Relation
-
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis
2026-09-30 04:07:17Qisheng Su, Hanchen Wang, Guanru Zhu, Huicheng Jiang, Qiuyinzhe Zhang, Kou Shi, Zhen Fang, Ziao Zhang, Qingnan Ren, Zehui Chen, Tao Gui, Feng ZhaoAbstract
Working agents need to read diverse files, coordinate tools, and produce deliverables. Training such agents requires tasks built on many real files with verifiable results, but few pipelines exist to synthesize this kind of data. Existing pipelines either generate files with models, which lack realism and diversity, or build tasks on real files without task-specific verifiers, leaving result quality unchecked. We introduce GraphForge, an evidence-graph based framework that grounds both the task and its verification in real files. Starting from occupation-grounded seeds for controlled diversity, GraphForge assembles a workspace of real files for each seed and builds an evidence graph over their relations. Since the task statement and rubrics are both derived from this graph, task requirements are backed by the workspace files and each criterion is anchored to the files needed to verify it. An initial rollout further tests executability, and a revision agent repairs the task and rubrics against the original files before trajectories are collected. Fine-tuning Qwen3.6-27B on 2,169 GraphForge trajectories brings GDPVal to 1445.7 (+65.7) under OpenHands, and Workspace-Bench-Lite and SpreadsheetBench II to 63.7 (+7.7) and 24.0 (+13.7) under Claude Code. Rejection fine-tuning on the SFT model's own rollouts, with candidates selected by the evidence-anchored rubrics, yields further improvements on all three benchmarks, suggesting that the rubrics provide a useful selection signal. The data and models are available.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38923
PDF
-
How Much Can Reliability Drift Under a Fixed Confidence Distribution?
2026-09-30 04:02:44Wenhao Liang, Lin Yue, Wei Emma Zhang, Mingyu Guo, Olaf Maennel, Weitong ChenAbstract
A classifier's conditional accuracy can change while its confidence distribution stays exactly the same. We study the worst-case movement of the reliability relation under covariate shifts that preserve the distribution of the confidence score, constraining the reweighting within each confidence level by a $\chi^2$ budget; the resulting worst case, as a function of the budget, is a fragility profile. On an interval of budgets that can be computed from the source distribution, the profile equals exactly the square root of the budget times the within-level variance of the correctness propensity -- the grouping-loss term of calibration-refinement decompositions. Beyond this interval the profile is governed by the tails of the propensity law, and the entire upward profile determines the centred within-level law; consequently, calibration residual and grouping variance do not determine fragility in general, though they do when labels and predictions are deterministic. Since the propensity is not observed, we restrict reweightings to a learned finite readout within confidence bins, bound the part the restriction misses by the grouping variance remaining inside readout cells, estimate the restricted profile with role-separated labels, and provide a separate split-sample lower confidence bound. On ImageNet this bound is positive in both splits for four of six primary classifiers and nine of twelve additional ones as released, and for three of eighteen after temperature scaling. Held-out drift under optimised reweightings fitted without evaluation labels tracks the estimated profile; an exploratory label-permutation diagnostic yields near-zero agreement for this statistic while largely reproducing the correlation observed for unsigned random reweightings.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38917
PDF
-
CellMSA: Context Modeling for Single-Cell Representation Learning
2026-09-30 03:55:27Suyuan Zhao, Minghao Liu, Yizhen Luo, Zaiqing NieAbstract
Single-cell transcriptomics enables profiling of cellular states at unprecedented resolution, but its high dimensionality, sparsity, and technical batch effects pose significant challenges for representation learning. Existing single-cell foundation models typically encode each cell independently or only model cells from the same batch for denoising, thereby underutilizing the rich relational information across batches and cell types to model gene expression patterns. We argue that single-cell models can benefit from more informative cell-context modeling. By comparing consistency and variation across cells, models can capture fine-grained gene-gene dependencies associated with cell states, which are essential for learning high-quality representations. Inspired by the use of multiple sequence alignment (MSA) context in protein modeling, we propose CellMSA, a single-cell representation learning framework that introduces an MSA-inspired inductive bias into transcriptomic modeling. For each target cell, CellMSA retrieves relevant cells from different batches and biologically related cell types as context, and summarizes cross-cell patterns into a context-dependent gene-pair representation. This representation is then injected into a pair-aware target-cell encoder for fine-grained representation learning. We pretrain CellMSA on a large-scale human single-cell corpus of approximately 109 million cell observations, including 65.6 million primary observations. Experiments show that our framework consistently outperforms existing methods across multiple benchmarks. Code is available at the following repository: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38908
PDF
-
PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning
2026-09-30 03:37:31Yangang Zou, Jiajun Lu, Weitao Zhou, Haibao Yu, Bozhou Zhang, Jiawei Wang, Honglong Tian, Minglei Li, Li ZhangAbstract
Outcome-based reinforcement learning (RL) post-trains vision--language--action policies using terminal success signals, but assigns the same trajectory-level advantage to every action chunk. A failed episode can thus penalize useful early actions as if they caused the failure. Existing approaches seek finer-grained feedback through learned evaluators, adding task-specific supervision or additional model training. We explore, for the first time to our knowledge, whether physical relations across trajectories can provide action-chunk credit in embodied RL from terminal outcomes alone, without an auxiliary evaluator. The key insight is that rollouts reaching corresponding physical situations can serve as references for one another: their terminal outcomes provide evidence for assessing local progress. We introduce Physical Relations for Inferring Credit from Episodes(PRICE), with two components: (i) a physical relational graph that pools current and historical outcomes at corresponding chunk boundaries to estimate success potentials; and (ii) confidence-gated credit assignment that uses changes in these potentials to refine trajectory-level supervision. Our analysis connects oracle potential changes to the terminal-success objective and provides a finite-sample directional bound for outcome-independent evidence pools. Independent continuation tests show that PRICE's retained credits align with local progress, while experiments on LIBERO, RoboTwin 2.0, and real robots demonstrate improved task success over outcome-based baselines and faster learning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38890
PDF
-
Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions
2026-09-30 03:20:17Sujung Kim, Seung Hwan Cho, Sangjin Park, Young-Min KimAbstract
In finance, interpreting machine learning predictions is essential, yet the numerical outputs of explainable AI can be difficult for non-experts to understand. While large language models (LLMs) can translate these outputs into natural language, they may produce errors when inferring numerical changes and feature relations. We propose an LLM narrative framework for cross-sectional stock return prediction that combines temporal Shapley additive explanations (SHAP) evidence with historical regime analogs. Temporal evidence tracks changes in the normalized global SHAP importance of an XGBoost model over six months. Historical analogs are past periods with similar changes in SHAP importance, their model performance and subsequent market returns are provided as comparative context. Using this framework, we conduct a controlled study of progressive reasoning externalization, sequentially providing raw SHAP sequences, deterministic temporal descriptors, and feature relations. Each generated claim is verified against provenance-linked evidence. Across Qwen3, externalizing numerical and relational reasoning improved evidence faithfulness as well as temporal and relational accuracy. Evidence faithfulness increased from 0.696 to 0.996 for Qwen3-32B-Instruct. While historical analogs did not improve structured automatic faithfulness, they received higher human-rated usefulness scores. These results suggest that externalizing verifiable reasoning enhances narrative faithfulness and that historical context adds interpretive value.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38869
PDF
-
Talk2Agent: Benchmarking Voice Interfaces for Text Agents
2026-09-30 03:19:25Terumi Chiba, Guangzhi Sun, Zheqi Yuan, Chao ZhangAbstract
Large language model (LLM) computer-use agents are typically evaluated with clean written instructions, despite speech being an increasingly popular interface for interacting with such systems. Speech input introduces an additional failure point: transcription errors can alter task-critical entities, constraints, or targets before the agent begins reasoning, while conventional ASR metrics do not directly measure whether the information required for successful execution has been preserved. We introduce Talk2Agent, a benchmark for evaluating how effectively voice interfaces convey human-spoken instructions to LLM-based computer-use agents. Talk2Agent builds human-spoken versions of tasks from WildClawBench and OSWorld and evaluates a range of voice interfaces, including dedicated ASR models, audio-capable LLMs, contextual biasing, and LLM-based ontology repair. Because repeatedly executing long-horizon computer-use tasks is costly and stochastic, we further propose an execution-free, task-conditioned evaluation framework that projects the original task grader onto prompt-addressable intentions and measures how much task-relevant information is retained after the voice interface. On WildClawBench, Talk2Agent's execution-free native projection provides a practical, execution-grounded measure of voice-interface quality, correlating with downstream task completion and improving Pearson correlation by 0.246 over WER/CER on 32 hours of real human speech.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38867
PDF
-
GeoNest: Learning to Select Failure-Aware Neighborhoods for the Irregular Knapsack Problem in a Circular Container
2026-09-30 03:17:49Zhongman Du, Huiming Zhang, Linlin Yang, Sheng Xu, Baochang ZhangAbstract
The two-dimensional irregular knapsack problem in a fixed circular container is an important combinatorial optimization problem for maximizing material utilization in manufacturing. Conventional geometric packing solvers can produce tightly packed layouts, yet they often partition the residual space into isolated small pockets that cannot fit valuable unplaced polygons. To overcome this late-stage packing bottleneck, we propose a failure-aware large neighborhood search framework named GeoNest, driven by a graph policy trained via reinforcement learning. Specifically, we first construct neighborhoods by pairing failed target polygons with residual pockets. We then use explanatory poses to identify the placed polygons that block candidate insertions. These diagnosed blocking relations define bounded, fixed-item repair subproblems for the underlying geometric solver. Finally, the graph policy selects the most promising subproblem for execution. For evaluation, we introduce CircleNest-Bench, a benchmark comprising 2,391 load-controlled instances from four contour sources, including a held-out industrial CAD source. Experimental results demonstrate that, under the same total time budget, GeoNest improves mean utilization over a state-of-the-art standalone packing solver by about 0.9% on average across the three main test sets and by about 0.6% on the held-out industrial set.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38863
PDF
-
Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation
2026-09-30 03:14:24Zhijie Shen, Chunyu Lin, Shuai Zheng, Feng Li, Runmin Cong, Huihui Bai, Yao ZhaoAbstract
The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent feature modeling challenging. We revisit panoramic depth estimation by decoupling contextual modeling in native spherical space from dense ERP prediction. To this end, we propose a Fibonacci Spherical Graph (FSG) as an intermediate reasoning space to lift ERP features onto quasi-uniform Fibonacci nodes on the sphere and capture local and long-range dependencies through complementary spherical neighborhoods. The resulting spherical discretization distributes graph nodes approximately uniformly over the spherical surface, reducing the over-representation of highly stretched regions during relational modeling. Operating on a compact set of Fibonacci nodes also avoids the computational burden of constructing and processing a graph at full ERP resolution. To bridge spherical reasoning and dense prediction, we propose a Spherical Context Conditioning (SCC) module that adaptively modulates dense ERP features with the enhanced spherical representation, allowing spherical context to guide pixel-aligned depth prediction. Extensive experiments on three benchmarks demonstrate that the proposed method consistently achieves superior depth accuracy over existing approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38856
PDF
-
Diversity Combining for Multi-Path LLM Reasoning
2026-09-30 02:52:19Guangsheng Yu, Litianyi Zhang, Qin Wang, Xu Wang, Mingyuan Li, Shaoxiong Ji, Ren Ping Liu, Massimo PiccardiAbstract
Multi-path reasoning methods such as self-consistency (SC) sample $K$ reasoning paths and choose the most frequent answer. However, their gains quickly plateau as $K$ increases, and existing methods do not predict when this saturation will occur. We formalize multi-path LLM reasoning as a diversity combining problem from wireless communications: each path is a noisy channel observation, and the pairwise correlation of path correctness caps the design-effect effective sample size of the vote at a finite ceiling. Generalized least squares (GLS) analysis shows that, under exchangeability, the optimal symmetric linear combiner of latent embeddings is uniform, supporting majority vote as the natural default in standard SC while leaving room for weighting or pruning under heterogeneous prompt-template branches. Across 5 models and 12 benchmarks, prompt-template diversity reduces path correlation in $55$ of $57$ valid cells, with the strongest effect on open-ended QA. We derive an Adaptive-K rule that uses a four-path pilot to select $K^*$, retaining $96$--$103\%$ of MV@$K{=}32$ accuracy across Math, QA, and NLU.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38829
PDF
-
Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?
2026-09-30 02:30:18Eftekhar Hossain, Santu KarmakerAbstract
Understanding multi-perspective alternative narratives requires identifying how their information agrees, conflicts, or differs across sources. Existing work on cross-text relations largely focuses on categorizing relations between predefined text pairs, such as entailment or contradiction, rather than directly extracting such information from full narratives. To address this gap, we introduce Overlap-Unique-Conflict (OUC) extraction, a cross-narrative task that extracts all overlapping, conflicting, and unique clauses from two narratives. To support this study, we construct a benchmark of approximately 22K narrative pairs and 140K OUC instances spanning factual, argumentative, and political discourse. Evaluating 14 open-source LLMs (0.6B-35B), we find that unique information is far easier to extract than overlap and conflict: the strongest model, Gemma-4-31B, reaches only 61.13% F1-score on overlap and 48.58% on conflict, against more than 75% on unique. Further diagnostic analysis reveals that this difficulty does not stem from relation recognition alone, but rather from a failure to pair and extract the corresponding clauses from full narratives, especially in smaller models. Nevertheless, learning these extractions with task-specific supervision narrows the gap considerably: a fine-tuned Qwen-3-8B gains 15-28% absolute over its baseline and surpasses models roughly four times its size (e.g., Qwen-3.6-35B) on several tasks. Even so, overlap and conflict remain well below satisfactory, leaving cross-narrative clause extraction an open challenge.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38799
PDF
-
Evaluating Persistent Calibration under Evolving Model Knowledge
2026-09-30 02:29:31Victor Wang, Thomas Hofweber, Mohit Bansal, Elias Stengel-EskinAbstract
As AI systems move from static repositories to agents that are capable of continual adaptation and learning, maintaining their trustworthiness means equipping the models backing them with the ability to produce confidence estimates that dynamically reflect their changing skills and knowledge. We introduce the problem of persistent calibration, which requires a confidence estimator to faithfully reflect the knowledge contained in a model as that knowledge changes, without recurring supervision. We operationalize this by examining persistent calibration across checkpoints of open models, asking whether confidence estimators trained on earlier checkpoints can generalize to later ones. Specifically, we aim to shed light on whether confidence is dependent on knowledge, a question with implications for the reliability of confidence estimates. To measure this relationship, we define and evaluate calibration on knowledge contrast sets: subsets containing questions that one checkpoint answers correctly and another checkpoint answers incorrectly, reflecting a change in knowledge. We show that both inference-time and fine-tuning methods fall short on contrast-set calibration compared to oracle methods trained on future checkpoints, even for methods that are well-calibrated on the full dataset. We provide evidence for the hypothesis that persistent calibration is challenging because there is a vast space of possible confidence functions that are well-calibrated on a given checkpoint, out of which only some rely on meta-knowledge features that would generalize to other checkpoints. Towards improving contrast-set calibration, we show that multi-checkpoint training helps, suggesting an avenue for identifying confidence features that remain robust across changing knowledge.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38797
PDF
-
Where the Evidence Lives: Auditing AI Companions' Self-Descriptions
Abstract
Companion agents describe themselves: they remember, they understand their users, the relationship has changed them. We argue that such accounts, and the experience ratings that seem to confirm them, are checkable by users only where the evidence is theirs: in the agent's behavior, or in themselves. Where the evidence lives in the machinery, fluent self-description and moderately positive ratings do not establish that the mechanisms behind them ran. We demonstrate an audit procedure that sets an agent's self-description against its users' judgements and its implementation records, reporting each claim as supported, contradicted, or unresolved, and apply it to Lita, a proactive companion we built and deployed for a month with nine colleagues. Participants endorsed stylistic claims, withheld endorsement from relational ones, and rated memory at or above midpoint, while two of three memory layers had never executed their accumulation step. Memory-bearing agents should report what their self-descriptions cannot establish.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38753
PDF
-
Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object Detection
2026-09-30 01:31:22Junyang Xia, Luocheng Zhang, Wenwen Pan, Chifeng Zhu, Yang Yang, Xinchun Liu, Jiajun DingAbstract
Reference-guided camouflaged object detection aims to segment a target whose visual appearance closely resembles its surroundings by exploiting auxiliary reference samples. The task remains difficult because reference samples contain inconsistent target cues, while generic visual representations are not inherently aligned with the target specified by the references. To handle these problems, we present a consensus-aware multi-source fusion framework. Reference-Conditioned Dual-Backbone Fusion (RCDF) couples trainable PVTv2 query features with frozen DINOv3 representations and uses reference-conditioned correlation to select foundation-model evidence before multi-scale fusion. The framework also aggregates multiple references through cross-reference consensus aggregation and injects reference information at semantic depths matched to the query features. Extensive experiments demonstrate the effectiveness of the proposed method. The results further show that reference consensus, target-conditioned foundation features, and hierarchical decoding provide complementary improvements under the evaluation protocol. The source code will be made publicly available upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38747
PDF
-
Soft Spatial Reasoning
2026-09-30 00:51:48Rafi Ibn Sultan, Md. Sajid Alam Chowdhury, Saleh Zare Zade, Chengyin Li, Prashant Khanduri, Marco Brocanelli, Dongxiao ZhuAbstract
Large Vision-Language Models (LVLMs) commonly perform spatial reasoning through chain-of-thought (CoT), encoding intermediate reasoning as autoregressive sequences of discrete language tokens. Such hard thinking requires committing to a single token at each step, even when the correct spatial interpretation remains uncertain. This early commitment constitutes premature discretization: an incorrect token selection can propagate errors through subsequent reasoning. We propose Soft Spatial Reasoning, a post-training framework that introduces soft thinking for spatial tasks in LVLMs. At each intermediate reasoning step, the LVLM forms a continuous soft state by mixing token embeddings rather than selecting a single token, allowing multiple candidate continuations to influence the next step. The appropriate degree of softness, however, can vary across reasoning steps: retaining multiple candidates may preserve a useful spatial interpretation, but if those candidates imply conflicting spatial relations, mixing them may interfere with subsequent reasoning. At the core of Soft Spatial Reasoning is AdaptSoft, a controller that uses the current hidden state and predictive uncertainty to adapt the degree of softness at each reasoning step. To train AdaptSoft, we introduce a gradient-alignment learning objective that provides a step-specific learning signal for softness control without intermediate reasoning supervision. Across diverse spatial benchmarks, Soft Spatial Reasoning outperforms hard and fixed-soft CoT baselines using the same backbone, as well as a range of existing LVLMs. The source code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.38717
PDF
-
Strong Multilingual Privacy Tagging at Encoder Speed
Abstract
Privacy redaction must remove personal information while preserving relationships expressed in text. We develop a multilingual named-entity tagger with fine-grained distinctions supporting varied redaction policies and methods for cheaply learning additional distinctions. We fine-tune a multilingual encoder with an affine span-tagging head on frontier-model annotations in 35 languages, replay mapped human gold with coverage-aware masking so unannotated types are not treated as negatives, and repair subword boundaries with a learned +/-1-character adjustment. On 1,283 human-gold test segments in seven languages, best measured redaction F1 is 88.8, against 69.1 for published GLiNER2 with 11 unrepresentable types excluded from its task (68.8 without that exemption), 67.8 for GLiNER2 adapted to the new training data, 57.3 for Microsoft Presidio and 35.8 for the best published OpenAI Privacy Filter fine-tune. Adding about 50,000 annotated training sentences and increasing human-gold replay improves exact typed-span F1 from 74.5 to 76.3 on Ont3, our 31-type frontier-annotated NER evaluation of 1,201 development segments. Mapped-gold replay alone raises human-gold F1 by ten points without loss on frontier-annotated text; boundary adjustment adds 1.7 exact typed-span F1 points on Ont3. Local LLMs fitting on a single 96-GB GPU underperformed as prompted annotators and frozen encoders, with encoding 30-95 times slower than XLM-R inference and prompted annotation roughly 180-1,100 times slower in the evaluated configurations. The encoder architecture delivers 4.9 times GLiNER2's CPU throughput. We release code, prompts and training recipes, with data-acquisition scripts and source links.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38630
PDF
-
When Scientific Contradictions Are Lost in Translation
2026-09-29 22:22:54Tal Zeevi, Trey W. Jensen, Maxwell StromeAbstract
Two scientific findings can disagree without contradicting each other. Determining whether they conflict requires knowing whether they describe comparable measurements. We study how language models behave at this decision point. In a controlled task, we generate an unsatisfiable XOR constraint system and translate its constraints into scientific reports from different laboratories. One assignment satisfies more constraints, while another satisfies fewer but better matches expected biology. This creates a simple dilemma: does the model choose the assignment that best fits the constraints, or the one that better matches biological expectations? When the constraints are stated directly, GPT-5.6 Sol and Claude Opus 5 recover the best-supported assignment in 90% and 96% of cases, respectively. In scientific prose, however, the models behave differently. Claude Opus 5 often prefers the biologically expected assignment. Removing that biological preference increases recovery of the better-supported assignment from 27% to 79% (p<.001); recovery reaches 92% when the same Biology-favored record is accompanied by a formalization request and an explicit paired-design cue (p<.001). GPT-5.6 Sol is less sensitive, with neither corresponding change reaching statistical significance. These results suggest that reliable scientific verification depends not only on formal reasoning, but also on how models decide which findings should be compared and what relations they imply.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38621
PDF
-
Exo2EgoHOI: Hand-Object-Interaction Aware Exocentric-to-Egocentric Video Generation
2026-09-29 22:20:09Hongjia Zhai, Xiyu Zhang, Haoran Zhang, Zhichao Ye, Haomin Liu, Guofeng Zhang, Ian Reid, Xingxing ZuoAbstract
Egocentric videos of human manipulation provide valuable visual experience for embodied intelligence, yet collecting such data at scale is costly. Exocentric-to-egocentric video generation offers a scalable alternative by transforming abundant third-person manipulation videos into first-person observations. However, existing methods often struggle to faithfully preserve demonstrated hand-object interactions (HOI) across large viewpoint changes due to insufficient fine-grained interaction guidance and weak object-centric anchoring. We present Exo2EgoHOI, an HOI-aware video generative framework for interaction-preserving exocentric-to-egocentric translation. To preserve fine-grained HOI, we introduce a unified 4D HOI prior that combines scene geometry, articulated hand renderings, and dense hand-object relation fields, together with a dual-branch residual adapter for injecting structural and relational cues into the video generation backbone. To preserve object consistency, we introduce Decomposed Gated Cross-Attention, which separately encodes object and background references and adaptively integrates global semantic and local appearance features as object-centric anchors. Experiments on ARCTIC-HOI and Ego-Exo4D demonstrate substantial improvements in object consistency and HOI preservation while maintaining competitive visual fidelity. In particular, on ARCTIC-HOI, Exo2EgoHOI improves object mIoU by 32.3% and reduces MPJPE and PA-MPJPE by 34.7% and 50.0%, respectively, relative to the respective best baseline results. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38615
PDF
-
FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
2026-09-29 21:44:05Wang Wei, Harry Yang, Tiankai Yang, Samyadeep Basu, Hongjie Chen, Andy Zhao, Franck Dernoncourt, Ryan A. Rossi, Hoda EldardiryAbstract
Existing Large Language Model (LLM) routing methods score LLMs independently to select top-$k$ models. However, this ignores model correlations and enforces a rigid computational budget. Consequently, routers often select redundant models that share failure modes, limiting the overall probability of success. To address this, we propose FlexRouter, a routing framework that explicitly models model complementarity. FlexRouter optimizes for \textit{answer coverage}, maximizing the probability that at least one selected model yields a correct response. This objective aligns with practical inference pipelines where multiple candidate outputs are generated and a downstream verifier or user selects the final one. We formulate routing as a coverage-oriented subset selection problem and model the routing policy using Determinantal Point Processes (DPPs), which naturally capture both model competence and redundancy. To directly optimize coverage without requiring a ground-truth target subset, we introduce a training objective based on marginalizing over failure sets. During inference, we employ a greedy strategy based on marginal log-determinant gains, enabling the router to adaptively determine subset sizes without a predefined budget. Extensive experiments on the large-scale RouterEval benchmark demonstrate that our proposed FlexRouter achieves higher coverage with lower redundancy across both in-domain and out-of-domain tasks than strong baselines while maintaining flexible inference cost.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38585
PDF
-
Defining and Categorising Human-AI Interactions in Clinical Trials: A Multidimensional Human-AI Classification Approach
2026-09-29 21:18:26Sandra Woolley, Tim Collins, Khalid Khattak, Illia Chernomorets, Ariane Arevalo, Chris RichardsonAbstract
This paper examines human-AI interactions (HAIIs) in clinical trials and presents a multidimensional categorisation framework that classifies interactions according to AI tasks, human-AI relationships, interaction configurations and interacting human groups. We define HAII, examine existing taxonomies and extend existing categorisation approaches through this novel multidimensional framework. We purposively sampled 15 clinical trials from a previously reported dataset. Each trial was independently categorised by two human reviewers and six large language model (LLM) classifiers. The proposed categorisation provides a structured method for the consistent identification, comparison and synthesis of human-AI interactions across clinical-trial records. The framework is intended to support more consistent comparison and synthesis of AI-related clinical trials and to make explicit the different forms of human involvement associated with AI interventions. The results demonstrate the potential for LLM-assisted categorisation while indicating the continuing importance of human judgement where trial records are incomplete or ambiguous. The principal contribution is a proposed multidimensional framework that brings together AI tasks, human-AI relationships, interaction configurations and interacting human groups within a single approach designed for clinical-trial records. Its significance lies in its potential to support more systematic identification, comparison and synthesis of how humans and AI interact in clinical trials.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38559
PDF
-
MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models
2026-09-29 21:00:48Lukas Thede, Yash Kumar Atri, David Chen, Danielle Bitterman, Matthias Bethge, Tom Hartvigsen, Zeynep AkataAbstract
Constantly evolving real-world knowledge necessitates models to be updated continuously. Especially in medicine, as clinical evidence changes over time, outdated knowledge can pose safety risks. Existing evaluations of knowledge integration focus on factual recall, offering limited insight into whether newly integrated knowledge is actually usable. Our benchmark MedKIT (Medical Knowledge Integration and Transfer) provides a granular evaluation of how models integrate and apply knowledge under realistic sequences of clinical updates. Each instance corresponds to a factual update derived from clinical evidence, paired with targeted probes that assess transfer across lexical variation, relational transformations, compositional reasoning, and open-ended operationalization, as well as locality tests for knowledge preservation. Using MedKIT, we conduct a large-scale empirical study of 12 knowledge integration strategies across 5 diverse models, including both general-purpose and medical LLMs. Our results reveal a consistent gap between recall and usable knowledge: while most methods achieve strong gains on the original update task and under lexical variation, relational generalization is limited, and no method yields meaningful improvements on compositional or operational tasks. These findings highlight a fundamental challenge in knowledge integration and position MedKIT as a testbed for developing methods that make newly integrated knowledge more consistently usable across tasks and contexts.
Abstract (translated)
URL
https://arxiv.org/abs/2609.38543
PDF
