Review
-
CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review
2026-09-04 14:55:33Jicheng Zhou, Kemou Li, Kahim Wong, Zheyuan Li, Zhuan Shi, Fengpeng Li, Haiwei Wu, Jiantao ZhouAbstract
Recent reports during the AAAI-27 review cycle highlight the risk of reviewers coordinating bids for reciprocal assignment advantage. Prior work treats bidding, reviewer assignment, and review manipulation as separate stages, leaving the lifecycle effects of collusive bidding unclear. Real-world analysis is further constrained by typically unobservable collusive intent and the lack of counterfactuals for the same conference. Motivated by this gap, we introduce \alg, an end-to-end multi-agent simulacra framework for studying reviewer assignment integrity by holding the conference environment fixed and configuring LLM-driven reviewer agents with honest or collusive policies. We further develop an affinity-guided collusive bidding strategy that uses mutual reviewer-paper affinities to construct collusion rings and select target papers, producing expertise-consistent rather than arbitrarily targeted attacks. Controlled experiments show that collusive bidding more than doubles target-paper capture and that assigned colluders score target papers about two points higher than honest co-reviewers, while conference-wide effects remain comparatively modest. Evaluated bid-phase detectors provide only limited evidence of collusion: in a fixed-triplet detector stress test, native positive-bid graphs are confounded by benign affinity, while a Very-High-only diagnostic view enables precise but low-coverage local recovery.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05227
PDF
-
A Human-in-the-Loop Framework for AI-Assisted Scoring in Large-Scale Writing Assessment
2026-09-04 13:47:29Mar\'ia Eugenia Curi, Germ\'an Capdehourat, Isabel Amigo, Magdalena Romano, Rosana Serra, Adri\'an Silveira, Andr\'es PeriAbstract
The integration of artificial intelligence (AI), particularly large language models (LLMs), into educational assessment has opened new opportunities to enhance the efficiency and scalability of grading processes. This study presents the design and validation of an AI-assisted scoring framework for written responses in a large-scale national assessment. The proposed approach focuses on short written texts of approximately 150-200 words and incorporates a human-in-the-loop strategy to preserve assessment quality while reducing manual workload. The study is grounded in a real operational context, using data from two recent editions of a nationwide test, each comprising approximately 5,000 student responses. We analyze the alignment between AI-generated scores and human raters across multiple rubric dimensions, as well as the impact of the proposed decision flow on pass/fail outcomes. Results show moderate to high agreement between the model and human evaluations in most dimensions, supporting the feasibility of AI assistance in this setting. Moreover, the proposed correction workflow identifies cases where human review is most valuable, enabling a more efficient allocation of expert effort. The findings suggest that AI-assisted scoring can be safely integrated into large-scale assessment processes only when combined with carefully designed human oversight. The paper concludes by discussing practical implications for deployment in national assessment systems and outlining future research directions, including longitudinal monitoring of model-human alignment and the analysis of potential cognitive bias introduced by AI-supported review workflows.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05143
PDF
-
TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents
2026-09-04 12:37:20Zhibo Yang, Chen Zhang, Yuewei Zhang, Hao WangAbstract
Autonomous coding agents are increasingly proposed as AI-scientist systems that conduct analyses and write research reports, but executing a prescribed analysis is not the same as making a discovery. Existing benchmarks are configured for reproduction: tasks, data, and rubrics are built around a hidden target study, and recovery of its result is rewarded. We present TruthInsightBench, a benchmark configured for discovery. Its 40 blind tasks, drawn from 40 peer-reviewed studies across 10 scientific domains, expose only a neutral scientific objective and frozen data; source conclusions, expected values, and analysis paths are withheld, leaving the agent to determine what claim the data support. A fixed LLM-based judge scores the evidentiary maturity of an agent's own claims along six dimensions, operationalized as 29 artifact-grounded items, with automated, deterministic aggregation and no per-instance human grading, so evaluation can be repeated automatically as agents evolve. On one frozen base model, four coding agents form a narrow plateau (58.4-60.3 of 100) with no statistically reliable pairwise separation: they execute and document analyses competently, with comparatively strong evidence auditability and novelty, but largely lack the discriminating acts that establish a trustworthy claim (controls, robustness, falsifiability, and cross-dataset generalization). The bottleneck is scientific judgment rather than coding, and genuine discovery remains out of reach. TruthInsightBench makes this gap a measurable target; data and scoring code are at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.05079
PDF
-
Artificial Intelligence in Equity and Crypto Markets: Progress, Profitability Evidence, and the Limits of Automated Investing
2026-09-04 09:19:51Linsen Zhu, Mengqing CaiAbstract
Artificial intelligence (AI) now supports investment workflows from data and prediction through research, portfolios, execution, and tool use. Technical capability, however, is not evidence of investment profitability. This critical state-of-the-art review examines public research available through 31 August 2026 on listed equities, exchange-traded funds, centralized crypto spot, perpetual futures, and on-chain markets. We organize evidence with an alpha-translation chain: point-in-time information must yield a stable signal, feasible positions, executable orders, and risk-adjusted returns after costs. Across machine learning, time-series foundation models, financial language models, reinforcement learning, and agents, the examined record shows real but mainly upstream progress in prediction, text processing, portfolio design, and workflow integration. Evidence is thinner for durable net performance. Temporal contamination, repeated selection, survivorship, weak benchmarks, implementation costs, venue mechanics, and capacity can break translation to net alpha. Strong historical results coexist with predictor decay, corrected look-ahead failures, mixed prospective evidence, and few audited live-capital records. Crypto adds informative state but requires separate treatment of spot, perpetual, and decentralized cash flows and execution. Within the public evidence examined here, no general AI architecture is shown to deliver persistent, cross-regime, capacity-aware net alpha. More credible claims require point-in-time data and models, decision-aligned objectives, joint portfolio--execution evaluation, controlled adaptation, prospective tests, and authority-matched governance. These conditions can improve evidence and implementation; they do not guarantee profit.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04917
PDF
-
From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments
2026-09-04 08:52:28Linsen Zhu, Mengqing CaiAbstract
Large language models become consequential agents when surrounding systems let outputs change external state. Models now call tools, operate interfaces, delegate work, retain state, inhabit generated worlds, and control robots or laboratory equipment. Such advances are often narrated as one march toward autonomy, conflating model competence, system integration, persistence, and safe authority. This critical review synthesizes primary research and official technical specifications available by 31 August 2026. We organize the evidence along delegated authority, temporal persistence, and environmental coupling, while separating model, harness, and environment. Within the evidence examined, action-interface expansion is documented more convincingly than robust completion, recovery, authorization, or independent verification. Model Context Protocol and Agent2Agent improve interoperability but do not establish trustworthy delegation; multi-agent organization adds specialization alongside cost and correlated failure. Persistent simulations and world models support training and planning but do not themselves demonstrate agency; robotics and self-driving laboratories establish bounded feasibility rather than unattended open-world reliability. We propose justified delegation as an analytical and normative heuristic, not an observed law or certified score: expand action scope only where evidence supports provenance, bounded authority, failure detection, safe recovery, and calibrated human control. This framing yields a research agenda for coupled model-harness evaluation, capability-based permissions, durable state, cross-agent accountability, and staged physical validation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04894
PDF
-
AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems
2026-09-04 08:30:36Qi Zhang, Yanlin Chen, Wenchao XiaoAbstract
Improving an industrial recommender is an iterative research-and-engineering process rather than a direct path from idea to deployment. In \textbf{DASHEN, NetEase's gaming-community app}, algorithm engineers typically identify promising directions from research papers, technical reports, and prior production experiments; reproduce or adapt the underlying methods; implement them in the production codebase; and evaluate the resulting models through training and offline experiments. Promising candidates are then advanced to online A/B tests, and those demonstrating robust gains are submitted to Launch Review---the internal gate for full-traffic rollout. Large language models (LLMs) can assist with individual stages of this workflow, but the overall process remains human-dependent without a harness that can reliably coordinate them across long-running, often multi-day experimental cycles. We present \textbf{AutoLR}, initially built as \textbf{Auto Launch Review} and later extended upstream into an autonomous research-to-launch harness. AutoLR combines three system mechanisms: a \textbf{multi-expert council} that debates and adversarially reviews proposals; a \textbf{deterministic evidence-weighted exploration--exploitation selector} that allocates a limited trial budget across candidate directions and uses Council reranking; and a layered knowledge system that combines external research, production-system knowledge, and DASHEN-specific domain knowledge---such as game communities, player characteristics, and content-interaction patterns---with posterior evidence from configurations, patches, logs, failures, and offline outcomes. LLM agents perform semantic reasoning and code generation, while deterministic controllers retain authority over execution, metric extraction, guardrails, and persistent state transitions.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04871
PDF
-
Dynamic Heterogeneous Graph Representation Learning: A Survey
2026-09-04 06:17:19Huan Liu, Pengfei Jiao, Jie Yin, Hongjiang Chen, Zhidong ZhaoAbstract
Graph representation learning (GRL) serves as a canonical paradigm for modeling complex networks. However, real-world AI systems inherently manifest as evolving heterogeneous entities with complex interactions, posing significant challenges to static or homogeneous modeling. To address these complexities, representation learning for Dynamic Heterogeneous Graphs (DHGs) has emerged as a vital approach for learning low-dimensional representations that simultaneously preserve structural semantics and temporal dynamics. This survey presents the first systematic review of DHG representation learning methods. We first introduce a unified formal definition that encompasses both discrete-time and continuous-time DHGs from the perspective of temporal granularity. Building upon this formulation, we propose a novel algorithm-centric taxonomy that categorizes existing literature, including early embedding-based approaches, graph neural network (GNN)-based models, and relatively recent Transformer-based DHG methods, while explicitly highlighting their intrinsic modeling biases with respect to dynamic granularity. Furthermore, we summarize representative applications of DHG representation learning, along with commonly used datasets and benchmarks. Finally, we discuss promising research directions that guide future advances in this rapidly evolving field.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04779
PDF
-
Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges
2026-09-04 06:16:49Chenqi Li, Minghui Min, Dusit Niyato, Wei NiAbstract
Diffusion language models (DLMs) offer a non-autoregressive alternative for mobile edge agentic artificial intelligence (AI) by refining tokens through iterative denoising rather than left-to-right decoding. Compared with autoregressive Transformer-based large language models (LLMs), DLMs can update multiple uncertain tokens in parallel and exploit bidirectional context throughout the generation process, enabling more flexible quality-latency trade-offs beyond fixed sequential decoding. These properties are particularly attractive for edge agents, where partial refinement, early exit, and constraint-guided correction can reduce response delay and communication overhead while improving robustness under noisy, incomplete, or dynamic contexts. This survey reviews DLM foundations and analyzes their suitability for edge settings under latency, memory, energy, bandwidth, privacy, and reliability constraints. We cover resource-efficient architectures, training and inference acceleration, compression, edge/cloud deployment, communication-aware serving, Internet of Things (IoT)/wireless applications, and evaluation of DLM-based agents. We further discuss open issues in long-context state management, split inference, trustworthy execution, multimodal grounding, and reproducible benchmarking. The goal is to connect DLM modeling properties, including bidirectionality, parallel refinement, controllability, and quality-latency elasticity, with system-level requirements of future mobile edge intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04778
PDF
-
Building a research-software catalog with a coding agent: from hackathon prototype to public deployment
2026-09-04 04:31:51Kazuyoshi Yoshimi, Satoshi Terasaki, Gotai YamadaAbstract
Generative AI and coding agents can accelerate research software development, but they also increase the need for efficient software discovery and maintenance. We developed a repository catalog during a three-day hackathon and subsequently examined the engineering required to make it suitable for public deployment, including adversarial review, data-quality checks, browser-level validation, and publication safeguards. We then explored whether the lessons learned from this prototype could be transferred to a much larger, human-curated portal, through a retrieval agent under development for MateriApps that combines curated portal metadata, external documentation, vector search, and local language-model generation. Implementation with coding agents was rapid, but achieving reliable operation required substantial additional engineering: the most consequential problems were not crashes but silent failures that produced plausible yet incomplete or incorrect outputs, arising from incomplete data acquisition, misleading assessments, and retrieval or preprocessing failures. These observations suggest that AI-assisted software portals require explicit validation, monitoring, and repeated review, and that curated metadata and maintained documentation remain essential. The MateriApps work is exploratory and remains under active development, so the observations reported for it are preliminary; a comparable combination of curated metadata, automatically collected documentation, and retrieval-based assistance may nevertheless be useful for extending other research-software portals.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04711
PDF
-
Model Retirement Creates Reproducibility Risk in Biomedical AI Publications
2026-09-04 04:00:54Nathan Wolfrath, Meghan Conroy, Thomas Kosten, Dave Bell, Bhabishya Neupane, Jonah Kindel, Anjishnu Banerjee, Priya Deshpande, Bradley Taylor, Anai N. KothariAbstract
Background. Large language models (LLMs) are being adopted in biomedical research at a rapid and accelerating pace, yet commercial services that host many widely used models operate under deprecation schedules that can complicate scientific reproducibility. Methods. We searched PubMed for original research articles from 2022 through March 2026 that applied a specific LLM to a biomedical task. An extraction agent identified model names from 61,077 article abstracts with human reviewers validating a subset for extraction accuracy. Extracted model names were normalized to canonical model identifiers. Lifecycle data (release date, retirement date, status) were compiled for the 50 most frequently used models. Results. We identified 8,931 paper-model mentions spanning 5,242 unique publications after restricting the analysis to the 50 most frequently used models. Among these mentions, 77.7% cited a commercial closed-weight model. Overall, 42% involved a model that was already retired by the time of official publication or is scheduled to retire within two years of publication. The median interval from publication to model retirement was 538 days. Conclusion. Many biomedical publications using LLMs are on a trajectory toward computational non-reproducibility after publication. Model deprecation should be treated as a core reporting and preservation issue for biomedical research.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04699
PDF
-
Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle
Abstract
AI coding systems are moving from autocomplete and chat toward agents that can inspect repositories, edit multiple files, run tools, write tests, open pull requests, and work for long periods with limited supervision. This capability changes the bottleneck in software delivery. Recent field studies show meaningful gains in coding activity, but newer evidence also shows that those gains attenuate sharply between writing code and shipping reliable software. Review, integration, testing, security, deployment, and production operations remain constraining stages, while the economics are shifting from predictable per-seat licensing toward variable token, tool, sandbox, CI, and rework costs. This paper synthesizes peer-reviewed software-engineering research, university studies, benchmark audits, production reports from major technology companies, developer telemetry, and cost-management evidence released primarily from 2024 through September 2026. No new model experiment is claimed; numerical findings remain attributed to their original studies. The synthesis proposes four engineering concepts: the Agentic SDLC Throughput Paradox, Production-Qualified Change (PQC), the Verification Tax, and an Agentic SDLC Control Plane that allocates autonomy subject to cost, reliability, and human-attention budgets. An evidence-based horizon then maps today's supervised agents to future policy-bounded software factories. The central research question shifts from how much code an agent can generate to how much production-qualified value an engineering system can deliver per dollar, per reviewer-hour, and per unit of operational risk.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04681
PDF
-
VISTA: Dense Multi-Label Classroom Coding with Vision-Language Models
2026-09-03 23:13:56Andrew Franck, Brendan Ng, Ben Fitzgerald, Zane Derrod, Chris Cianci, Chris CraneyAbstract
Video-language benchmarks are usually constructed by the dataset authors without published reliability statistics, leaving the noise floor of the construct unknown. We argue that multimodal benchmarking benefits from methods taken from research communities that have already invested in strategies to ensure reliability. We illustrate the case with the Classroom Observation Protocol for Undergraduate STEM (COPUS): a 24-code multi-label observation instrument with a decade of peer-reviewed reliability literature. We recast COPUS as a video benchmark for multimodal foundation models, where it provides a dense set of structured labels (a 24-dimensional binary vector every 2 minutes across a 50-90 minute lecture), an externally validated vocabulary, and established literature that provides a per-code reliability target based on human evaluators. Annotations in our evaluation corpus are produced by a 5-person human-evaluator panel whose consensus matrix is our reference. We propose VISTA, a baseline that runs MiniCPM-V-4.5 over a dense sliding window, refines its per-window outputs with a lightweight multi-layer perceptron (MLP) head trained on top of the frozen backbone, and max-pools the resulting predictions onto the 2-minute COPUS grid. On three held-out chemistry lectures, VISTA reaches 80.1% restricted macro accuracy versus 74.9% for the zero-shot variant, with the largest residual errors on visually similar instructor codes and on rare audio-dependent codes. We characterize three systematic failure modes (audio-partial observability, fine-grained group-work discrimination, long-tail recall) and release the benchmark tooling, prompts and baseline code at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04550
PDF
-
Towards a universal language of concepts: A survey
Abstract
Humans can learn and generalize novel concepts from sparse data because they express knowledge in rich structural formats. In this paper, we propose that programs are a strong candidate for universal representation of concepts. We review computational models of concept learning that use programs as their concept representation and evaluate their contribution toward a universal representational language.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04528
PDF
-
GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion
2026-09-03 20:03:20John Seon Keun Yi, Joshua R. Minot, Dokyun LeeAbstract
Large language models deployed in high-stakes settings frequently generate plausible but ungrounded claims. Standard retrieval-augmented generation (RAG) pipelines offer limited remedy, since they retrieve isolated passages without tracking cross-document evidence relationships or quantifying uncertainty. We introduce GRACE (Graph-grounded Reflective Agent Copilot Engine), a framework that deconstructs LLM responses into atomic claims and grounds them against trusted knowledge priors within a weighted bipartite graph. Edge weights encode the closeness of each claim to the priors, enabling weighted centrality analysis that classifies claims as Grounded, Refuted, or Boundary. Such classification identifies not just hallucinations but also novel or contested claims at the frontier of the model's knowledge. To efficiently allocate human or agent resources, we formulate a Return on Attention (RoA) objective that defers a claim to expert review only when its priority-weighted uncertainty exceeds the cost of verification. Claims verified by experts are promoted to new evidence anchors, closing a validator-LLM evolutionary loop that expands the knowledge base across iterations. We evaluate GRACE across multiple language models and on datasets spanning both general and domain-specific knowledge. Our results show that our knowledge base serves as a reliable foundation for retrieval that outperforms RAG baselines, and that the RoA framework efficiently selects valuable boundary knowledge for expert verification. These findings demonstrate that graph-structured representations combined with expert-in-the-loop verification can mitigate hallucination at the system level rather than at the generation level. Code available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.04442
PDF
-
VERGE: Verification-Enhanced Refinement for Grounded Extraction of Early-Onset Colorectal Cancer Symptoms in Clinical Notes
2026-09-03 18:25:50Nikkie Hooman, Monarch Nigam, Amy E. Hughes, Rasmi G. Nair, Mehak GuptaAbstract
Early-onset colorectal cancer is increasing among younger adults, yet red-flag symptoms in this age group have no evidence-based guidelines for follow-up testing, and structured encounter data do not capture the detail needed to support early detection and inform follow-up, including symptom duration, context, and fam- ily history, an established colorectal-cancer risk factor. This study aimed to develop and evaluate an automated method for extracting six red-flag symptoms and family-history risk status from free-text clinical notes. We developed VERGE, an agentic workflow in which an initial label and evidence are proposed using retrieval-augmented generation, then passed through a bounded verification- refinement cycle that checks textual grounding and clinical validity, corrects and rechecks a claim until resolved or a limit is reached, and escalates unresolved claims for human review. VERGE was evaluated on 4,033 clinician-labeled note-finding pairs against a single-agent baseline, a rule-based clinical language-processing baseline, and an alternative underlying language model. Compared with the single-agent baseline, VERGE reduced false positive find- ings, improving precision from 0.764 to 0.849 and MCC from 0.681 to 0.730, a balanced gain across the precision-recall trade-off, and resolved most flagged errors autonomously, with human review required for only 1.5 percent of claims. These results indicate that a bounded, verification-based workflow can reduce unnecessary positive findings without sacrificing the ability to detect true ones. This approach offers a path toward more reliable and trustworthy clinical language-processing tools to support colorectal cancer risk assessment in younger patients.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04366
PDF
-
Last Translation Benchmark
2026-09-03 17:54:45Vil\'em Zouhar, Niyati Bafna, Mukund Choudhary, Maike Z\"ufle, Sara Rajaee, Pinzhen Chen, Jannis Vamvas, Sara Papi, Ona de Gibert, Bhavitvya Malik, Eliya Habba, Orfeas Menis Mastromichalakis, Patr\'icia Schmidtov\'a, Michelle Wastl, Sheriff Issaka, Leshem Choshen, Stella Biderman, Antonis Anastasopoulos, Jan Niehues, Rico Sennrich, Mrinmaya Sachan, Ond\v{r}ej Bojar, Kenton Murray, J\"org Tiedemann, Alham Fikri Aji, Philipp Koehn, Christof Monz, Alexandra Birch, Sowmya Vajjala, Chalamalasetti Kranti, Cristina Espa\~na-Bonet, Nobin Sarwar, David Kacz\'er, Shunta Asano, Malik Marmonier, Daban Q. Jaff, Vaisakhi Mishra, Hend Al- Khalifa, Gabriele Sarti, Sourajit Saha, Nils Rehlinger, Juan Daniel Cuervo Villa, Jonathan Tonglet, Saugata Purkayastha, Dominik Mach\'a\v{c}ek, Jagannathan Ramanujam, Heejin Do, Zuzana Nadova, Fred Philippy, Fabian Retkowski, Maria Lymperaiou, Silvia Casola, Hanna Yukhymenko, Shubhashis Roy Dipta, Sangwon Ryu, Andr\'es Jerez, Ron Keinan, Shuaib Shuaib Yusuf, Avantica Vempati, Maria Carmen Staiano, Sukannya Purkayastha, Adrian Cosma, Vitalii Babenko, Erivan Inan, Aviral Nigam, Wafa Aissa, Fatima Haouari, Venkata Prasanth Kumar Gummadi, Mehdi Jafarzadeh, Valentin Scourneau, Lukas Edman, Kaiser Sun, Shaomu Tan, Mohammad Sadegh Gholizadeh, Johannes-Rudolf David, Dipankar Srirag, Javier Garc\'ia Gilabert, Ruta Binkyte, Manar Ali, Ana-Maria Bucur, Sabry E. Farrag, Youssef Saber, Yihong Liu, Jean Maillard, Cojocaru Nicoleta, Xiaochuang Yuan, Sina Ahmadi, Philipp Mondorf, Kaustubh Dhole, Roman Wixinger, Shenbin Qian, Manuel Tuor, Sergey Troshin, Jonathan Yahav, Fida Mohammad Thoker, Amir Arsalan Rezapour, Lance Calvin Lim Gamboa, Manon Reusens, K\"atriin Kukk, Koel Dutta Chowdhury, Giuseppe Gallipoli, Christian Hoang, Shaswati Saha, Seth Aycock, Jan Koco\'n, Bo Chen, Linh Vu, Vatsal Venkatkrishna, Arafat Ahsan, Luan Thanh Nguyen, Hassan Soliman, Daryna Dementieva, Theresia Veronika Rampisela, Ngoc Quynh Tram Do, Marius Huber, Kazuki Egashira, Azmine Toushik Wasi, Vladislav Poritski, Mike Zhang, Deep Shah, Paul Gavrikov, Luis Frentzen Salim, David Africa, R. Damanhuri, Bello Umar Bello, Anumit Garg, Gengyu Rao, Pawan Sasanka Ammanamanchi, Kamile Dementaviciute, Andrianos Michail, L D M S Sai Teja, Dawei Zhu, Yi Fan, Wei Liu, Farhan Farsi, Elias Herranen, Sankalan Pal Chowdhury, Karen Sanchez, Farzad Shami, Ashok Urlana, Zimu Wang, Tomasz Limisiewicz, Priyaranjan Pattnayak, Marii Ojastu, Hongbin Na, Emilian Radoi, Chenyi Zhao, Carlos Hinojosa, Andrea Gregor de Varda, Zaid Alyafeai, Reem Alzahrani, Nehal Kathrotia, Alex Fl\"uckiger, Ulysses Sekai Tully Carr, Jimson Paulo Layacan, Guy Kaplan, Ritwik Tiwari, Rishit Dagli, Oksana Volchek, Isaac R Caswell, Bowen Yi, Blanka K\"ov\'er, Amir Hossein Yari, Aicha Chorana, Zhengxiang Wang, Selja Ker\"anen, Samuel Simko, Joy Olusanya, Jenny Chim, Enzo Doyen, Vivek Harsha Lakkamaneni, Sophia Conrad, Pouya Sadeghi, Panayiotis Panayiotou, Luis Lara, Jannatul Nayem, Eran Yahav, Debanshu Das, Antonia Karamolegkou, Anmol Goel, Aishik Mandal, Tommaso Cerruti, Raoyuan Zhao, Mykola Haltiuk, Thura Aung, Naser Almousa, Amir Hossein Kargaran, Rachel Bawden, Qiaoyuan Zheng, Mateusz Lango, Beni Egressy, Fidel Rodr\'iguez Vel\'asquez, Natchapon Jongwiriyanurak, Minh Ngoc Do, Marco Gaido, Lena Libon, Dzmitry Kuzmin, Badal Nyalang, Antoine Taroni, Andrei Niculae, Abdulaziz Nura Kani, Rushikesh Zawar, Marek \v{S}uppa, Beatrice Savoldi, Andreas Simons, Rayyan Merchant, Ilai Yaron Levy, Francesco Pinto, Ziyi Yang, Yolanda Xavier, Samuel Frontull, Muhammad Ravi Shulthan Habibi, Kenneth Enevoldsen, Harris Abdul Majid, Francesca Padovani, Tim Graf, Tatiana Bielakova, Sharifa Djurabaeva, Shaoxiong Ji, Raia Abu Ahmad, Pavel Stepachev, Jirui Qi, Ayush Sunil Munot, Alireza Pakniat, Ayla Rigouts Terryn, Yuxing Lu, Yurii Paniv, Xiyan Fu, Tosin Adewumi, Sunisth Kumar, St\'ephane J. P. S. Thunus, Shree Harsha Bokkahalli Satish, Shayan Bali, Prakhar Gupta, Papa Abdou Karim Karou Diallo, Matija Akrap, Marko Culjak, Krist\'yna Onderkov\'a, Joseph Attieh, Esrael Teferi Tensay, Elisabeth Fittschen, Beno\^it Sagot, Jingwei Ni, Yu FanAbstract
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, standard benchmarks for machine translation are approaching saturation. Further, automatic translation metrics are unreliable, vulnerable to reward-hacking, and provide unactionable assessments. Even gold human evaluation is not problem-free, because it often lacks reproducibility, objectivity, and scalability. Overall, this prevents us from tracking objective progress in the field and identifying pathways for improvement. We introduce the Last Translation Benchmark, a collection of human-authored and peer-reviewed examples (texts, images, audio, videos) that break leading machine translation models. We also present a new evaluation approach: each example comes with handcrafted verification rules describing concrete failure cases on that example, therefore allowing reliable and actionable future evaluation. The Last Translation Benchmark is a live dataset that accepts ongoing contributions. The latest version is LTBv1, containing accepted contributions prior to September 1st 2026, with future releases planned as new data is continuously collected.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04173
PDF
-
SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents
2026-09-03 17:53:34Xin He, Yanlin Wang, Mingwei Liu, Jiachi Chen, Hongyu Zhang, Guanbin LiAbstract
Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measure whether generated patches pass functional tests and overlook review-derived acceptance constraints (review constraints) that often influence whether a patch is acceptable in real-world software development. We introduce SWE-Gate, a repository-level benchmark for software engineering agents that explicitly evaluates review constraint compliance alongside functional correctness. SWE-Gate derives review constraints from real pull request review comments and synthesizes repository-level repair instances around these constraints. Each instance provides separate functional and constraint tests, together with non-compliant and gold patches, enabling explicit separation between issue resolution capability and review constraint compliance. We construct SWE-Gate with 303 repository-level repair instances spanning 75 open-source Python repositories across diverse software domains. Experiments with four LLM backends spanning different capability levels under a common coding-agent scaffold reveal a substantial gap between functional success and success under the complete repair specification: among 644 repairs that pass the functional tests, 221 fail to satisfy the provided review constraints. These findings show that functional-only evaluation overestimates agents' ability to satisfy the full requirements of repository-level repair tasks. The replication package including code, data, and experimental results is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04167
PDF
-
Environment Evolution for Terminal Agents
2026-09-03 17:26:33Zhiyuan Fan, Tinghao Yu, Yuanjun Cai, Jiang Zhou, Jiangtao Guan, Jincheng Liu, Yun Yang, Dingxin Hu, Zhuo Han, Xing Wu, Feng Zhang, Lilin WangAbstract
Scaling interactive and verifiable environments is critical for training terminal agents. As frontier models become more capable, environments synthesized from scratch become less challenging and thus provide limited learning signals. Recent co-evolution methods iteratively synthesize environments near the model's learnable frontier based on weaknesses exposed during rollouts. However, their dependence on on-policy rollouts limits generalization and the continuous provision of learning signals as the model becomes stronger. In this paper, we propose environment evolution, which incrementally increases environment difficulty off-policy and schedules the evolved environments generation by generation during training to provide continuous learning signals. We derive three evolution directions that influence environment difficulty from the multi-turn learning objective and then implement evolution along these directions through a loop-engineered multi-agent harness. Quantitative rollout experiments with Hy4 preview, Claude Opus 5, and GPT-5.6 Sol show that environment evolution consistently produces more difficult environments. We validate its effectiveness on Qwen3.6-27B and Qwen3.6-35B-A3B through simple long-horizon RL training, improving their performance by 14.4 and 18.0 percentage points on Terminal-Bench 2.1, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04128
PDF
-
When Models Edit Too Much: On the Fidelity of Minimal Code Edits
2026-09-03 16:36:05Tongyao Zhu, Wei Hern Lim, Min-Yen KanAbstract
Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful repairs should also be minimal, reviewable, and faithful to the original implementation. We study over-editing, the tendency of a model to rewrite code beyond what is required to fix a bug. We construct an evaluation framework from 400 BigCodeBench problems by injecting controlled AST-level corruptions into reference solutions, giving each repair task a known minimal patch. Across frontier LLMs, over-editing is widespread even among strong models like GPT-5.5: high Pass@1 can coexist with unnecessarily large edits and added cognitive complexity. A preservation instruction substantially reduces this behavior, lowering average excess Levenshtein distance from 0.195 to 0.131, reducing added cognitive complexity by 26.6%, and increasing Pass@1 by 2.3 points. However, these gains do not simply follow from a larger reasoning budget or larger models. We next ask whether minimal editing can be learned directly during post-training. We observe that supervised fine-tuning overfits to seen corruption patterns, whereas reinforcement learning gives the best out-of-domain edit-fidelity and performance-retention trade-off. These results position edit fidelity as a distinct axis of code-repair quality and show that it can be measured and learned.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04061
PDF
-
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
2026-09-03 16:26:20Lin Shi (Audrey), Haowei Lin (Audrey), Zixuan Zhu (Audrey), Xiaoyue Zhou (Audrey), Xiang Li (Audrey), Xiangning Lin (Audrey), Yaxuan Deng (Audrey), Han Xu (Audrey), Yuangang Li (Audrey), Shanda Li (Audrey), Zizhao Chen (Audrey), Hanwen Xing (Audrey), Harsh Raj (Audrey), Bo Chen (Audrey), Quan Shi (Audrey), Steven Dillmann (Audrey), Yipeng Gao (Audrey), Puneesh Khanna (Audrey), Ruofan Lu (Audrey), Chao Beyond Zhou (Audrey), Michael Yang (Audrey), Robert Zhang (Audrey), Siyuan Chai (Audrey), Jiayu Chang (Audrey), Yizhao Chen (Audrey), Xiaokun Chen (Audrey), Yiwei Dai (Audrey), Wenting Yang (Audrey), Hange Liu (Audrey), Minghao Liu (Audrey), Zihan Wang (Audrey), Adnan El Assadi (Audrey), Benedikt Stroebl (Audrey), E. Kelly Buchanan (Audrey), Han Meng (Audrey), Junwei He (Audrey), Longxuan Yu (Audrey), Radin Shayanfar (Audrey), Yukyung Lee (Audrey), Zhikang Dong (Audrey), Allen G Hart (Audrey), Anjiang Wei (Audrey), Anurag Kashyap (Audrey), Arpandeep Khatua (Audrey), Audrey Jixin Zheng (Audrey), Chengrui Ma (Audrey), David Heineman (Audrey), Dubing Chen (Audrey), Hai-Anh Trinh (Audrey), Haishuo Fang (Audrey), Hefan Zhang (Audrey), Hui Shen (Audrey), Issa Sugiura (Audrey), Jiankai Sun (Audrey), Jiechao Gao (Audrey), Junhong Lin (Audrey), Junnan Li (Audrey), Kai Yang (Audrey), Lei Hsiung (Audrey), Maoyu Wang (Audrey), Mengze Tang (Audrey), Nabil Omi (Audrey), Negin Raoof (Audrey), Nicholas Edwards (Audrey), Octavia Guo (Audrey), Orfeas Menis Mastromichalakis (Audrey), Pengliang Ji (Audrey), Przemys{\l}aw Hejman (Audrey), Qi Qi (Audrey), Qunshu Lin (Audrey), Richard Zhuang (Audrey), Rui Yang (Audrey), Ruichen Zheng (Audrey), Ryan Marten (Audrey), Shaghayegh Fazliani (Audrey), Shizheng Hou (Audrey), Sicong Jiang (Audrey), Sijie Li (Audrey), Song Bian (Audrey), Terry Yue Zhuo (Audrey), Tianqing Wu (Audrey), Tom Tang (Audrey), Wanjia Zhao (Audrey), Weihao Xuan (Audrey), Wenhua Liang (Audrey), Xian Liu (Audrey), Xin Lan (Audrey), Xuan Zhang (Audrey), Xuandong Zhao (Audrey), Yanchuan Tang (Audrey), Yifan Jiang (Audrey), Yijiang Li (Audrey), Yitong Guan (Audrey), Yizhi Li (Audrey), Yonghui Liu (Audrey), Yuheng Tang (Audrey), Yujun (Audrey), Mao, Yunfei Zhao, Yuxin Wang, Yuxuan Tang, Zhenheng Tang, Zhifei Li, Ziruo Wang, Ziyu She, Kaiyuan Liu, Iheb Chaabane, Yuxin Tang, Xiangyi Li, Andy Konwinski, Boxuan Li, Leon Liangyu Chen, Alex Dimakis, Nicholas Carlini, Soroush Vosoughi, Di He, Etash Guha, Benjamin Feuer, Mike Merrill, Ludwig Schmidt, Alex ShawAbstract
Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of 8 models spanning capability tiers across 54 benchmarks; every model is run with Terminus-2 and with one of 3 native harnesses. This enables a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Index, a curated set of 82 difficult, diverse, and high-quality tasks spanning 29 benchmarks, refined from the adapted suite through difficulty filtering, AI and human audit, and an audit-and-fix loop. Harbor-Index preserves the challenge and breadth of large-scale agentic evaluations while being affordable to run; no evaluated model-harness configuration exceeds 30% pass rate, and the strongest (GPT-5.5 with Codex) reaches 28.0%. We release the adapters, evaluation results, in-depth analysis, and Harbor-Index as open-source artifacts to support more reliable and comprehensive evaluation of language-model agents.
Abstract (translated)
URL
https://arxiv.org/abs/2609.04298
PDF
