GAN
-
How Language Models Organize Task Information
2026-10-20 06:43:48Kaiyang Wan, Yuxia WangAbstract
Dense linear probes assess task readability from language model (LM) representations, but do not directly reveal how many features suffice for prediction. We measure readout sparsity with \(k^*\), the smallest feature count found by a fixed search protocol that recovers 95% of dense-probe AUROC above chance. We evaluate 19 LMs from five labs on 14 core tasks. Ten base models give the nine reliably readable tasks similar feature counts and nearly the same order. This agreement extends to the selected features themselves, which on three tasks show cross-model response correspondence beyond class-mean differences and a label-correlation-matched null. Instruction-tuned deployment selectively reduces \(k^*\), with both weights and input format contributing. In controlled synthetic experiments across 20 models, successfully learned targets admit single-feature readouts, whereas readable controls require tens of features. Reference-model \(k^*\) is associated with label requirements across eight students, following an empirical scaling of \(N^*\propto(k^*)^{0.65}\). After continual learning, saved heads can fail while linear readability remains high, and recovery requires fewer labels than initial task learning under the tested procedures. Pruning reduces linear readability, with wider pre-pruning readouts generally associated with larger losses. These findings distinguish task readability from readout sparsity and establish their complementary value for predicting learning requirements and diagnosing LM changes.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27724
PDF
-
How Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection
2026-10-20 06:30:27Kaiyang Wan, Forrest Sheng Bao, Amin Ahmad, Yuxia WangAbstract
Under matched conditions, classifier-head fine-tuning (\textsc{cls}) paradigm consistently outperforms the LLM-as-Judge sequence-to-sequence (\textsc{s2s}) on binary hallucination detection. We trace this gap to the representations induced by the two objectives. Static analysis shows that \textsc{cls} learns a task-specific discriminative direction, pushing hidden states into a clear two-cluster geometry with stronger class separation and linearly decodable label information. By contrast, \textsc{s2s} relies on the pretrained language-modeling head to make decisions. This minimizes the pressure to reorganize representations, leaving the hidden states much closer to the pretrained backbone. Our analysis also reveals that the \textsc{cls} signal saturates before the final layer, after which upper layers form a plateau of statistically interchangeable and largely redundant representations. However, endpoint redundancy alone does not show whether these layers are dispensable during training. Further training-dynamics analysis reveals 1) a lower pretrained substrate, 2) a narrow upper-middle \textbf{InfoWindow} where task information emerges, and 3) a later-synchronizing upper plateau that mirrors this signal. This mechanism motivates us to remove layers above the InfoWindow. Truncating 31\% of the network leaves accuracy unchanged within seed noise on Qwen3-4B and 8B and cuts latency by $1.4\times$. The same depth fraction, fixed before any analysis of the target models, transfers to Llama-3.2-3B and Mistral-7B-v0.3, and the layer structure behind it reappears there and on QNLI and SST-2. We hope this helps guide efficient task-specific LLM design.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27711
PDF
-
PanoGraphGS: Unifying Panoptic Segmentation and Hierarchical 3D Scene Graphs with Gaussian Splatting
2026-10-20 06:15:59Jinghan Gao, Siyu Wang, Dongyu Feng, Yiyuan Pan, Rong XiongAbstract
3D scene graphs support language-guided navigation by organizing physical entities and their containment and spatial relations into hierarchical maps. Building such structured maps requires a scene representation that consistently distinguishes semantic regions and object instances across viewpoints. To this end, we present PanoGraphGS, a unified framework that integrates panoptic 3D Gaussian representation learning with hierarchical 3D scene graph construction. The framework learns semantic and instance features on shared Gaussian geometry. Prototype-based semantic learning and association-based instance learning produce consistent panoptic predictions across viewpoints. The learned representation supports novel-view panoptic segmentation and direct Gaussian-level panoptic decoding. A semantic-aware scene graph module further recovers a floor-room-stuff-object hierarchy with containment and spatial relations. We further release NaviGS, a real-world dataset for panoramic scene understanding. The dataset provides 3DGS, mesh, RGB, semantic, and depth data. For 3D scene graph identification, PanoGraphGS outperforms the strongest evaluated baseline in object-node accuracy by more than 50\% points on average across Replica and NaviGS. PanoGraphGS also achieves state-of-the-art performance among the evaluated methods in 2D panoptic segmentation. These results demonstrate the effectiveness of PanoGraphGS in both hierarchical 3D scene understanding and 2D panoptic segmentation. The project website is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27696
PDF
-
A Two-Way Street: Surveying the Interplay between Code-Mixing and Native Languages in Text and Speech
Abstract
Systems for code-mixed (CM) text and speech rarely start from scratch. CM data is scarce, so most work borrows from the languages being mixed, which we call native languages. This transfer can also run in reverse, when CM data is used to improve models for the native languages. Existing surveys focus on processing CM itself, and none brings the two directions together. This paper fills that gap with a systematic survey of transfer in both directions, across text and speech. We organise the surveyed work in a taxonomy of transfer direction, route and modality. Through this taxonomy, we find that most transfer runs from native languages into the CM setting. The reverse direction is younger, and in it code-switching mainly helps by aligning the two languages. Text and speech work share methods but rarely cite each other. On a shared speech benchmark, native data helps more than new architectures. These findings point to open challenges, such as how much native and CM data to mix in training, and how to evaluate CM text written in different scripts.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27631
PDF
-
Learning Inter-Graph Interactions Between Heterogeneous Substructures of Chemical Systems
Abstract
Complex chemical systems containing heterogeneous substructures are common in real-world applications. Various physical phenomena of the complex chemical systems are derived from the interactions between the heterogeneous substructures. However, existing graph representation learning methods for inter-graph interactions assumed graph-level interactions between homogeneous structures, such as organic molecules and inorganic crystalline materials. We propose a data descriptor of the complex chemical systems and a graph neural network for learning inter-graph interactions between organic and inorganic compounds. We applied the proposed method to predict the physical properties of hybrid solar cell materials containing heterogeneous substructures, which have received significant attention for sustainable energy resources. By learning heterogeneous inter-graph interactions, the proposed method achieved state-of-the-art accuracy in predicting band gaps of 1,682 hybrid solar cell materials.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27614
PDF
-
HiQGS: Hierarchical Spatiotemporal Querying for Feed-Forward Gaussian Reconstruction
2026-10-20 04:10:57Qiaowei Miao, Qifeng Cheng, Yijing Guo, Yuru Xiao, Ziqian Ni, Sheng YangAbstract
Feed-forward Gaussian reconstruction from sparse posed monocular frames requires reasoning over observations that vary jointly in viewpoint and time. Existing methods either predict Gaussian primitives from observation-aligned features or aggregate multi-frame information through compact latent queries. However, the former tightly couples Gaussian allocation to individual frames, while the latter does not explicitly structure observed evidence according to its temporal relation to the requested timestamp. Consequently, evidence across spatial scales, viewpoints, and timestamps can be difficult to align and integrate. We present \textbf{HiQGS}, a query-based hierarchical framework for feed-forward Gaussian scene reconstruction from sparse monocular frames. HiQGS introduces a \textbf{Hierarchical Spatiotemporal Encoder} that organizes multi-resolution geometry-appearance visual features according to image location, observation time, and camera pose, thereby preserving complementary appearance and structural cues. Our \textbf{Time-Adaptive Decoder} use target timestamp queries the resulting hierarchical representation to retrieve relevant spatiotemporal evidence and predicts the corresponding Gaussian scene state. Experiments on static and dynamic scene reconstruction benchmarks demonstrate strong rendering quality and geometric accuracy, validating the effectiveness of hierarchical visual encoding and target-time-aware Gaussian querying.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27604
PDF
-
From Encoding to Generation: Towards Empathetic Large Language Models
2026-10-20 04:10:24Samhita Bollepally, Takashi Yamauchi, Marissa WestAbstract
Empathetic interaction involves two distinguishable capacities: representing another person's emotional state (cognitive empathy) and generating an appropriate response to that state (affective empathy). We apply this distinction to examine how emotion-related information is internally organized, selectively attended to, and carried through response generation in Llama-3.2-3B-Instruct across 10 emotion categories from the EmpatheticDialogues dataset. Layer-wise linear probing revealed a broad middle-layer region of peak emotion-category decodability, with the layer-11 L2 probe achieving 63.6% held-out accuracy against a 10% chance level and a 54.6% TF-IDF lexical baseline. During response generation, emotion-related user tokens received 1.89 times as much attention per token as other utterance tokens, concentrated across layers 10-15. Target-emotion alignment then decreased from a mean cosine similarity of 0.239 for input representations to 0.125 for generated responses, with positive drift in 77% of examples and the largest shifts for angry and furious. Emotion-category representation, attention allocation, and response-level alignment therefore emerge as distinguishable components of model processing that can be analyzed through a functional cognitive-affective empathy framework. These findings provide a foundation for monitoring emotion representations during generation and leveraging models' existing affective structure to support more naturally empathetic responses without relying on external prompting or explicit emotion conditioning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27603
PDF
-
TRCM: Topology-Aware Route-Consistency Modeling for Robust Neural Vehicle Routing
2026-10-20 03:32:20Peiheng Jian, Zhenwei Wang, Tiehua Zhang, Lei Zhang, Zhishu Shen, Ruibin Bai, Zhijun DingAbstract
Neural combinatorial optimization has enabled fast constructive solvers for the Capacitated Vehicle Routing Problem (CVRP), yet most autoregressive models still construct solutions through sequential node selection and represent route organization only implicitly. We investigate whether route-level customer co-assignment can be modeled explicitly and used to guide this node-level decision process. To this end, we propose TopologyAware RouteConsistency Modeling (TRCM), which reuses node representations from a standard autoregressive construction pipeline to predict pairwise same-route probabilities and injects them into customer selection as a route-consistency signal. Because sameroute supervision is both class-imbalanced and structurally uneven, TRCM combines structure-preserving augmentation with Topological Entropy (TE)- based reweighting to emphasize locally ambiguous customer pairs. Under matched decoding budgets, TRCM reduces the optimality gap from 3.67% to 3.28% on CVRP50 and from 2.11% to 1.99% on CVRP100; under 8-fold augmented inference, it reduces the CVRP100 gap from 1.61% to 1.49%. On XML100, TRCM*8Aug improves the average objective by 0.24%, with larger gains on several structurally informative factors. A controlled demand-reassignment test over 500 variants further shows more concentrated objective fluctuations. These results support explicit route-consistency modeling as an effective structural principle for autoregressive neural routing.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27568
PDF
-
AudiPsy: Evidence-Grounded Multimodal Reasoning over Spoken Counseling Conversations for Depression Assessment
2026-10-20 03:31:15Chuanbo Zhu, Run Luo, Weibo Zhao, Yue Li, Kun Qian, Qiang Qu, Yike Guo, Minghuan Tan, Wei XueAbstract
Depression assessment from counseling speech requires integrating textual and acoustic psychological evidence across turns, yet existing end-to-end classification approaches lack explicit multimodal evidence interpretation and context-aware reasoning. We propose AudiPsy, an evidence-grounded omni-LLM for depression assessment over spoken counseling conversations. AudiPsy employs an Observation-Assessment-Summary (OAS) paradigm to integrate dialogue transcripts, textual and acoustic emotions, and textual-acoustic emotion incongruence into structured reasoning. OAS incrementally organizes multimodal observations, performs contextualized assessment, and maintains an evolving dialogue summary for subsequent turns. To support this framework, we construct AudiPsy-Counsel, a synthetic spoken counseling conversation corpus with multimodal context augmentation, and develop a unified three-stage curriculum for depression-oriented reasoning. Experiments on DAIC-WOZ demonstrate superior depression assessment performance over specialized depression detection methods and general-purpose speech/omni-LLMs, along with improved reasoning quality, while supplementary evaluation on EATD-Corpus supports AudiPsy's applicability to naturalistic conversations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27567
PDF
-
Automated Multi-Agent Organization Design: From Architecture Search to Organizational Learning
2026-10-20 02:47:52Shao-Jun Xia, Yuner Zhang, Huixin Zhang, Di Wang, Yifan Jiang, Liangxi LiuAbstract
Agentic system design is increasingly shifting from hand-crafted prompts and workflows toward automated search over agentic programs and interaction structures, with multi-agent systems receiving growing attention. Yet a central question remains unresolved: when does an automatically generated multi-agent structure exhibit a functionally meaningful division of responsibility? We argue that automated multi-agent design should move beyond searching for effective architectures toward identifying which responsibilities are functionally necessary, how they should be allocated, and when they should change. To explore this, we propose Automated Multi-Agent Organization Design (AMOD), which treats organization itself as a first-class design object, explicitly modeling how agent teams are composed, what functional responsibilities the agents assume, how they coordinate, and how collective decisions are made. We formulate AMOD as an execution-driven design loop. For each task, an automated designer instantiates an organization by assigning functional responsibilities and coordination rules to a set of agents. After execution, task outcomes, intermediate artifacts, and interaction traces are examined to identify which responsibilities may be missing, duplicated, or ineffective, and the organization is revised accordingly. We also propose testing discovered responsibilities by removing them, replacing them with generic roles, or changing their assignment under matched resource budgets, with complementary evaluations. AMOD provides a principled foundation for evidence-based and adaptive multi-agent organization design.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27531
PDF
-
MemDev-Bench: Does Memory Help Code Agents?Benchmarking Memory Systems over Real Repository Histories
2026-10-20 02:39:26Guorui Chen, Tao Liu, Zhenzhen Huang, Yidan Zhang, Liyu Jiang, Shuoyuan Wang, Hanchen Sun, Xu He, Dong Li, Yihan Hu, Jianye Hao, Lei FengAbstract
Code agents increasingly work on evolving real repositories, and memory systems aim to help them reuse earlier experience. However, such experience is diverse and evolving, so it remains unclear how memory systems organize it and thereby affect code agents. Existing benchmarks cannot answer this reliably because they lack either temporally valid histories or control over prior-task relevance. In this paper, we present MemDev-Bench to evaluate how memory systems affect code agents over diverse repository histories. It pairs each task with relevance-annotated earlier tasks from the same repository to build histories with controlled relevance. We also build an automated pipeline that reliably makes these earlier tasks executable and verifiable, producing 4,869 historical tasks for 555 base tasks. Based on MemDev-Bench, our systematic evaluation of memory systems across diverse development scenarios yields three main findings. (1) Memory mainly improves fine-grained localization and editing, increasing functional correctness. (2) Memory also causes failures on otherwise solvable tasks even with related history, and unrelated history tends to increase such failures. These failures mainly stem from agents reusing memory without reassessing its applicability. (3) Compared with using memory systems, directly providing agents with raw historical trajectories substantially reduces their steps. Further analysis suggests that agents save these steps by reusing process information that compressed memories tend to omit. These results suggest that future memory systems should preserve process information and reassess memory applicability against current task context.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27524
PDF
-
HATCH: Hardware-Attested Task Chains for Verifiable Manipulation
Abstract
Capability claims in robot manipulation are unverifiable, and existing leaderboards are each closed, simulated, or gameable. We propose HATCH, a robot escape room: an openly specified, physically replicable, sensor-scored, and unrehearsable benchmark. Tasks span five skill categories at three difficulty levels and are chained so that the sensor confirming one task's completion unlocks the next, turning a room into a single long-horizon evaluation. Success is confirmed by instrumentation rather than human judgment, scoring is embodiment-agnostic, and object placements are randomized by a run-day seed. Entrants submit attested self-runs (uncut video, sensor logs, and the seed), with occasional organized events for calibration. Task specifications, build guide, bill of materials, and scoring rubrics are released under an open license.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27485
PDF
-
Privacy-Preserving Personalized Federated Learning for Medical Imaging
2026-10-20 01:41:12Md Morshedul Islam, Hossain Shahriar, Alfredo CuzzocreaAbstract
Federated learning (FL) is a distributed machine learning paradigm that reduces transmission costs, mitigates cross-border data sharing restrictions, and enhances privacy by keeping raw data on local devices. Clients in FL systems train local models and share only updates, which are aggregated by a central server. While this setup limits direct data exposure, FL remains vulnerable to privacy attacks. Existing attack and defense strategies have largely been developed for centralized systems, and adapting them to FL introduces new challenges due to its unique architecture and training workflow. In this work, we first propose a model inversion attack on FL systems using Deep Convolutional Generative Adversarial Networks (DCGANs) in the context of large-scale medical imaging. Our method operates under realistic assumptions about the attacker's knowledge and capabilities. We then examine the effect of client-side differential privacy (DP) in mitigating privacy leakage and incorporate personalized FL to improve model performance under DP settings. Experiments on the Brain MRI ND-5 dataset show that DCGAN-based attacks can reconstruct semantically meaningful synthetic images, revealing significant risks to the privacy of training data. Applying DP reduces attack success but introduces an accuracy trade-off, which is further overcome by personalized FL at each client side. We also evaluate how different aggregation algorithms affect both attack vulnerability and defense effectiveness, underscoring the critical role of aggregation strategies. The proposed attack-and-defense framework is model-agnostic and applicable to a wide range of FL-based systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27470
PDF
-
ProMemAgent: Long-Horizon Proactive Assistance with Context-Aware Prospective Memory from Sensory Perceptions
2026-10-19 23:47:50Lilin Xu, Linyang He, Kaiyuan Hou, Yuang Fan, Minghui Zhao, Xuhai Xu, Xiaofan JiangAbstract
Large language model (LLM) agents are moving beyond reactive responses toward proactive assistance that anticipates user needs without explicit requests. However, existing proactive agents primarily address immediate needs, while many everyday situations involve delayed intentions that can only be acted on hours or days later. Humans handle such intentions through prospective memory, the ability to remember to act on an intention when the right moment arises. In this paper, we introduce ProMemAgent, the first proactive agent to incorporate prospective memory over everyday sensory contexts for long-horizon proactive assistance. ProMemAgent organizes past sensory perceptions (e.g., egocentric video and audio) into context-aware memory, generating prospective cues and linking earlier events with subsequent developments for future retrieval. Given the current context, it retrieves relevant past events and performs memory-augmented proactive reasoning to determine whether assistance is needed. We further introduce CPMBench, the first benchmark for evaluating long-horizon proactive assistance over sensory contexts, comprising 1,000 instances across eight everyday categories. Extensive experiments show that ProMemAgent achieves the best memory retrieval performance and consistently outperforms all baselines on long-horizon proactive assistance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27400
PDF
-
An LLM-Based Agent for Legal Compliance Assessment: Architecture, Memory, and Evaluation in a Canadian and Quebec Context
2026-10-19 22:24:34Soukaina Alaoui Ismaili, Jean-Sebastien DessureaultAbstract
Checking whether a text complies with a body of law is slow when done by hand and fragile when done with keyword rules. This paper presents ComplianceAgent, the legal compliance sub-agent of COMPASS, a multi-agent framework that evaluates texts along four axes: digital sovereignty, carbon impact, compliance, and ethics. The agent relies on a large language model that scores a text on a fixed rubric, grounds its judgment in a reference legal corpus, and, when the score falls at or below a critical threshold, runs a corrective chain made of self-healing rewrites, a compliance label, an explainability report, and escalation to a human reviewer. We describe what the language model does at each step, how the memory of the agent is organized, and how the same implementation can be pointed at different reference corpora. We evaluate the agent in a Canadian and Quebec context, on a corpus of thirteen legal instruments that brings together federal and provincial texts, international treaties, and municipal documents of the City of Trois-Rivières. The evaluation relies on a hand-annotated gold standard of fifteen texts and combines classification metrics, a repeated-query stability test, retrieval precision, and a composite score. On this gold standard the agent separates every conforming text from every non-conforming one, its scores remain stable under repeated queries, and the index returns relevant passages.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27347
PDF
-
When Does an Added Planning Capability Create Operational Value? An Observable Evidence Standard
2026-10-19 21:21:20Yihua Xu, Yan Lyu, Jize Li, Jiani He, You Lin, Yidan Hu, Rubing QiangAbstract
Industrial artificial intelligence (AI) planning systems combine predictive models, optimization logic, controls, and governance rules, but improvement in the complete policy does not show whether one addition made an independent contribution or whether that contribution justifies its burden. We address this attribution problem with an observable evidence standard that separates opportunity to act, executed-plan change, operational consequence, equivalence, uncertainty, and operating scope. Using forecast-to-plan replay on Favorita, M5, and Walmart data, we apply the standard to heterogeneous planning additions. Three limits of single-indicator evaluation emerge. First, a composite policy can conceal negligible component contribution: one control changed only 15 of 681 executed plans. Second, changing execution does not guarantee stable benefit: the evaluated multi-period capability helped in several long-lead settings but was 7.6% more costly under tight capacity. Third, indirect evidence can prioritize review but cannot complete attribution. Independent runs produced different paths in 19 of 599 cases that a rule-based check predicted would be unchanged. Although a lower-cost diagnostic matched the full-evaluation winner in only 55.0% of cases, it selected an option within the $10^{-6}$ cost-equivalence tolerance in 79.5%; the remaining cases prevented the proxy from authorizing acceptance. These experiments establish capability-level contribution evidence; the organization completes the value decision by weighing it against implementation and sustaining burden. The resulting capability evidence record links the observations to validation, deployment scope, fallback, monitoring, redesign, and retirement decisions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27305
PDF
-
AutoRedClaw: Automated Red-Teaming for Claw-Style Agents
2026-10-19 20:15:39Hao Li, Tongyan Hu, Weidi Luo, Shanghao Shi, Xiaogeng Liu, Aiden Suh, Yulong Cao, Ning Zhang, William Yeoh, Yevgeniy Vorobeychik, Chaowei XiaoAbstract
Agent systems are shifting from task-scoped tool-use agents to persistent, personalized assistants such as OpenClaw. These claw-style agents maintain configuration files (e.g., this http URL), long-term memory, and reusable skills. Once poisoned, this persistent state is repeatedly reloaded into the agent's context, creating persistent threats across tasks and sessions. Existing security evaluation systems struggle to evaluate these complex claw-style systems since they rely heavily on manually constructed test cases and environments, which limits their scale and coverage; in addition, these manually designed cases quickly become outdated as agents evolve, and their evaluation settings leave a gap with how claw-style agents are deployed in practice. To address this, we introduce AutoRedClaw, an automated red-teaming framework that generates end-to-end attacks together with the environments needed to execute them. AutoRedClaw combines a strict quality-checking protocol with execution-based validation to ensure the correctness, realism, and effectiveness of generated samples, and adopts task-driven environment construction to keep costs low. To achieve broad coverage, it organizes generation along risk categories, attack strategies, attack stages, and attack surfaces, and uses experience-guided exploration to steer generation toward under-explored regions. AutoRedClaw achieves an effective attack rate above 30% at less than $0.10 per successful sample. From its outputs, we construct RedClaw-Bench, a 330-case benchmark that yields substantially higher attack success rates (ASRs) than AgentDojo, AgentDyn, and DTap. Across seven harnesses and four frontier models, most agent systems exceed 50% ASR, showing that our red-teaming pipeline provides a strong evaluation signal even for the most advanced agent systems. Our code and benchmark are released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27244
PDF
-
Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling
2026-10-19 17:58:11Tong Ding, Caiwei Tian, Dongmin Bang, Ming Y. Lu, Sophia J. Wagner, Andrew Zhang, Rowland Pettit, Long Phi Le, Faisal MahmoodAbstract
EHR foundation models promise scalable clinical prediction across health systems, yet their deployment is constrained by a tokenization bottleneck. The same clinical concept can appear as different ontology codes, local identifiers, synonyms, or free-text descriptions, which standard EHR tokenizers treat as unrelated symbols. A model trained on MIMIC-III with a closed-vocabulary tokenizer can use only 13% of eICU events. We introduce MEDIATOR, a discrete ontology-agnostic tokenizer that maps any clinical concept expressed as text into a shared vector-quantized codebook, turning EHR harmonization into open-vocabulary tokenization without manual mappings or a fixed vocabulary. Trained with synonym supervision and guided by enriched concept descriptions, code co-occurrence, and relation graphs, MEDIATOR collapses equivalent expressions while organizing distinct concepts in a medically meaningful discrete space. Used as the token interface of an EHR Transformer, MEDIATOR improves mean AUPRC over the strongest prior tokenizer by 4.0 points (8% relative) on 20 MIMIC-III tasks and by 8.6 points (29% relative) in zero-shot transfer to 14 eICU tasks, where it uses all events. The transfer gain combines coverage and representation, as MEDIATOR remains the best tokenizer under identical inputs (+1.0 and +1.9 points on operational and subcohort-mortality tasks). Same-encoder controls show that the text encoder drives in-domain accuracy, while the learned objectives of MEDIATOR drive transfer robustness and entity-linking quality. MEDIATOR also enables transferable attribution across hospitals.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27047
PDF
-
M-Plan: Comprehensive Planning For LLM Agents with Memory Arrangement
2026-10-19 16:30:42Ziyang Liu, Jiakang Yuan, Jiayuan Fan, Tao ChenAbstract
Large language model (LLM)-based agents have recently demonstrated outstanding performance in single-turn tasks, yet they continue to struggle with long-horizon tasks, particularly in environments without prior training. A key limitation of single LLMs is their difficulty in processing long contexts, which stems from weaknesses in continuous decision-making and reasoning capabilities. Although existing multi-agent systems (MAS) equipped with long-term memory bases can partially address this gap, they mostly rely on knowledge reuse or summarization, an approach that is often constrained by directly retrieval without any adaptation for the current task, while the retrieved memory may contain much history noises waiting to be preprocessed. In contrast, MAS characterized by task-specific guidance often lack long-term memory specifically designed for the guidance. To address these challenges, we propose M-Plan, a closed-loop MAS framework that integrates long-term and short-term memory. By combining global-local and past-current guidance, M-Plan enhances agents' performance on multi-turn tasks while maintaining a plug-and-play design. During task execution, agents receive task-specific milestones and insights, and are provided with local hints only when confusion arises, which form global-local guidance together. These guidance generation and utilization construct the short-term memory as well. After task completion, relevant information about the current task is optimized or reorganized before being sent to the long-term memory storage for future retrieval. The designments mentioned above build a comprehensive framework different from other individual long-term or short-term memory works. Extensive experiments on multi-turn tasks including ALFWorld, Webshop, and PDDL across diverse models demonstrate that M-Plan outperforms multiple baseline methods in both accuracy and efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27032
PDF
-
TRACE: Training-aware Robustness and Challenge Evaluation for Text-Vision Embedding Models
2026-10-19 07:38:29Pume Tuchinda, Tinnakit Udsa, Peerat LimkonchotiwatAbstract
Existing benchmarks for text-vision embedding models report aggregate scores that obscure whether performance comes from general capabilities, task-specific adaptation, or robustness to challenging tasks. We introduce TRACE, a Training-aware Robustness and Challenge Evaluation framework that reorganizes 168 tasks from various sources of datasets into three categories: General, Adaptability, and Challenge. Through controlled experiments on two text-vision embedding models, we show that combining general and adaptation data improves Adaptability performance by 7.67 and 7.09 points, respectively, while largely preserving General performance. However, Challenge performance remains below 5.0, with limited improvements from additional training data. Further analysis identifies multilingual and visual-document tasks as major weaknesses. Our findings demonstrate that data adaptation alone is insufficient to address these challenges, highlighting the need for methodological advances beyond data-centric improvements.
Abstract (translated)
URL
https://arxiv.org/abs/2610.26993
PDF
