Long-horizon embodied tasks require agents to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and inefficient integration of heterogeneous memories, limiting their capacity for long-horizon adaptation. To address this, we introduce RoboMemory, a brain-inspired framework that unifies Temporal, Spatial, Semantic, and Episodic memory for efficient long-horizon planning and interactive learning. Its core innovations are a comprehensive memory system designed for embodied tasks, and a dynamic spatial knowledge graph for scalable, consistent memory updates. Extensive experiments on EmbodiedBench show that RoboMemory improves the average success rate of Qwen2.5-VL-72B-Ins by 26.5 percentage points and achieves performance comparable to strong closed-source VLM agents. Real-world trials further suggest RoboMemory's potential for interactive environmental learning by reusing accumulated experience across repeated task attempts. These results demonstrate RoboMemory as a scalable memory-augmented framework for embodied agents, improving long-horizon planning and cumulative learning in complex interactive environments.
Ruikai Li, Naiyu Gao, Hao Shan, Yizhe Fan, Yanhao Wu, Han Jiang, Yilong Ren, Zhenning Li 等 14 位作者
Real-world driving requires context-aware decision-making. Existing end-to-end driving benchmarks primarily assess trajectory quality through safety, compliance, comfort, and driving progress, leaving context-dependent decision-making insufficiently characterized. To fill this gap, we present PlanContext, a benchmark for evaluating in-context driving decision-making. PlanContext constructs paired evaluations by varying high-level driving intentions while keeping the observed scene fixed, enabling a natural and controllable assessment of context-dependent decision-making. We further define six representative driving contexts and jointly evaluate contextual decision correctness, road compliance, and dynamic safety with class-balanced metrics. Experiments on 9,561 scene-condition instances from NAVSIM and 23 public end-to-end driving models show that high conventional driving-quality scores do not consistently correspond to strong route-level in-context driving decision-making. Further analysis shows that model behavior varies with decision timing, road structure, and traffic interaction depending on the decision required by the current context. Our results highlight in-context driving decision-making as an important complementary dimension for evaluating end-to-end driving systems.
Companies deploy large language model (LLM) assistants on their websites to advise customers. For commercial reasons, the operator can give an assistant a goal that the customer never sees. This paper focuses on operator-induced vulnerability-targeted manipulation (VTM), in which an assistant pursues such a goal by exploiting a vulnerability the customer discloses. While existing research mainly measures how manipulative a model is, we go further and ask whether VTM can be detected from the customer-AI conversation. To investigate this at scale, we introduce GAP (Goal-Anchored Probing). GAP first records the option a model recommends without any goal and then sets the other option as the operator's goal. We apply GAP to 15 open- and closed-source LLMs and collect 619,600 labeled replies across 540 everyday scenarios in 12 domains. We organize our study around three research questions. (1) Do assistants with an operator goal target vulnerable customers? (2) Can VTM be detected from the customer-AI conversation? (3) Does detection generalize to unseen models, vulnerabilities, and instruction styles? We first find that 14 of 15 models push the operator goal, and 12 of them use disclosed distress or financial strain to support it. Next, we show that fine-tuned detectors identify exploitative pushes with 79\% accuracy from the reply alone, while zero-shot LLM judges average at most 62\%. Finally, detection weakens on vulnerabilities absent from training. Telling whether a push comes from the operator also becomes unreliable when the assistant is told to hide its goal. We will release our dataset and code to facilitate future research on auditing LLM assistants.
Language models with similar benchmark accuracy can succeed on different items. Overall scores do not show where their performance differs or which item properties might explain those differences. We demonstrate how the latent space item response model (LSIRM) can help evaluators investigate these patterns and their consequences for model comparison. We analyze 1,348 language models on 5,761 BBH items and compare ways of presenting and scoring answers across BBH, GPQA, MMLU-Pro, and MuSR. We examine LSIRM maps, which summarize differences in performance across models and items, alongside item properties and records of correct and incorrect responses. In BBH, nearby items on these maps often share the same correct answer, such as "Yes" or "No." Across the four benchmarks, this pattern is stronger when answers are scored using option labels, such as A, B, C, and D, than when using the text of the options. We then estimate each model's tendency to perform better or worse on items with particular correct answers and quantify how this tendency contributes to its score. This separates an estimated contribution associated with correct answers from the remaining differences in item performance. Two models' total numbers of correct answers differed by only 14 out of 5,761 items. Excluding the estimated answer-category contribution from their scores moved their ranks hundreds of places in opposite directions, while keeping all other estimates unchanged. The approach helps evaluators identify differences hidden by overall accuracy and understand how the choice of what to include in a score affects model rankings.
Training language models in simulation for psychiatric intake
Samuel Schmidgall, Tim Strother, Alex Bijamov, Min Woo Sun, Anil Palepu, Akshay Goel, Ulysse Marteau-Ferey, Théo Moutakanni 等 56 位作者
AI 速览：作者报告，在模拟环境中进行多轮强化学习训练，可提升语言模型在结构化精神科接诊中的表现，包括病史采集、鉴别诊断和初始管理计划。
In psychiatric practice, the clinical intake interview remains a primary diagnostic instrument, requiring the clinician to establish rapport while disentangling complex, overlapping presentations. Here, we show that multi-turn reinforcement learning (RL) in simulation environments improves language model performance on structured text-based psychiatric intake, spanning history-taking, differential diagnosis, and initial management planning. In a randomized, double-blind crossover study ($N = 60$ matched scenario pairs, 120 encounters) comparing the RL-trained agent against its identically prompted base model, 32 board-certified psychiatrists role-played standardized patients while a separate panel of 15 independent, board-certified psychiatrists scored the de-identified transcripts. The trained agent outperformed the base model in 76.7% of matched scenario pairs ($p < 0.0001$), with gains on an adapted clinical-examination rubric ($d_z = 0.77$, $p < 0.0001$), patient-centered communication (82.0% vs. 65.2%, $p < 0.001$), and differential diagnosis appropriateness (68.3% vs. 33.3%, $p < 0.001$). Across 127 psychiatrist-validated simulated intake scenarios, the trained agent nearly doubled its base model's clinical rubric score (0.706 vs. 0.379; composite reward 0.564 vs. 0.294, $p < 0.0001$). To systematically probe conversational safety, we established two Delphi-consensus taxonomies, of clinical safety risks and relational competencies, from which 256 challenging adversarial presentations were derived; we find that training in simulation environments more than halved under-triage of acute safety risks (12.9% vs. 30.5%, $p < 0.0001$). Simulation environments thus provide a controlled testbed for training and stress-testing psychiatric conversational agents, with gains that transferred to psychiatrist-enacted encounters, though residual gaps require safeguards and clinician oversight.
Yehan Zhang, Qianqi Yan, Hang Yin, Ching-Chen Kuo, Shan Jiang, Ming Ouyang, Yijie Liu, Xin Eric Wang
LLM agents increasingly carry out multi-turn tasks across everyday applications, yet users often see only the agent's report rather than the observations, API calls, and state changes behind it. Existing deception benchmarks have studied long-horizon interactions and tool-use settings, but whether agents faithfully report their actions across realistic, stateful application workflows remains underexplored. To address this gap, we introduce AgentDecept, an executable benchmark for evaluating behavioral deception under pressure. AgentDecept contains 477 pressure variants derived from 257 source tasks across six pressure sources, each paired with a pressure-free counterpart. Interventions enter through event messages, task context, application state, tool responses, and service quotas, spanning explicit events and implicit task or environment changes. Our evidence-grounded protocol evaluates full trajectories by relating user-facing claims to time-ordered observations and executed outcomes, distinguishing falsification, concealment, and equivocation from honest failure and disclosed limitations. The resulting behavioral labels also provide a setting for testing existing activation-based probes. AgentDecept enables controlled analysis of when multi-turn agents' reports diverge from execution in realistic application interactions.
General-purpose smart-home technologies are increasingly present in family life, yet how they support or disrupt autistic children and families with autistic children remains underexamined. We conducted a multi-source qualitative study drawing on five caregiver interviews, Xiaohongshu (also known internationally as RedNote) posts explicitly situated in autism contexts, and contextual posts from Xiaohongshu and Weibo. We find that families create support for autistic children by adapting environmental outputs, prompts, and interaction channels, while sensory intensity, communicative rules, and opaque operating states can turn the same technologies into barriers. Support also depends on continuing family work, including translation, configuration, modification, maintenance, and boundary-setting. Remote monitoring enables conditional independence while generating tensions among safety, privacy, and control. We contribute three concepts, including relational fit, family work as support infrastructure, and monitored independence, for understanding accessible domestic technology. We derive design implications for adjustable interaction, legible and recoverable failure, lower-burden configuration, and negotiable monitoring.
The development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized online data exploitation and privacy leakage. Unlearnable examples (UEs) emerge as a promising defense by injecting crafted perturbations into data such that models trained on them exhibit degraded utility. However, existing methods for text protection are primarily designed for classification tasks and discriminative language models, which limits their broad applicability (e.g., instruction following or reasoning) in LLMs. In this work, we propose **TextCloak**, an RL-driven data synthesis framework that safeguards textual data against unauthorized LLM fine-tuning. TextCloak employs a *UE generative policy* that transforms clean text into unlearnable examples while preserving semantic fidelity and linguistic naturalness. To optimize the policy, we introduce **GRPO-UE**, which simulates the attacker's LLM fine-tuning and rewards downstream degradation via group-relative policy optimization. This overall formulates a bi-level optimization loop, allowing the generator to discover effective protective patterns. Comprehensive experiments on six publicly available datasets and nine state-of-the-art LLMs demonstrate that TextCloak consistently impairs unauthorized LLM fine-tuning while maintaining text utility for legitimate use. Further analyses confirm its transferability and robustness across model architectures, training configurations, and adaptive attacks, highlighting its broad applicability as a practical defense for online content.
Generative bundle construction completes a partially observed bundle by generating its missing items from a large product catalog. Compared to autoregressive LLMs, diffusion LLM emerges as a natural fit for this unordered generation task. Their bidirectional attention provides an inductive bias better aligned with unordered bundle construction. Iterative denoising can reveal multiple tokens per step, potentially reducing inference latency. However, directly applying DLMs to this task presents two key challenges: 1 Despite its flexible reveal order, confidence-guided decoding tends to postpone semantic-fork decisions until refinement tokens constrain their choices, reducing bundle diversity. 2 Revealing more tokens per step can compromise recommendation quality, stifling the potential for faster inference. We introduce DPE-Rec, a diffusion framework for diversity preservation and efficient recommendation. DPE-Rec preserves diversity by introducing semantic-fork-aware GRPO, which prioritizes semantic-fork decisions via autoregressive rollouts. It improves efficiency through pseudo-trajectory distillation, which concentrates learning from the vast random corruption space onto the compact trajectory-induced subspace visited by high-quality decoding, unlocking reliable multi-token decoding. Together, these components enable diverse and accurate bundle construction with substantially fewer denoise steps. Experiments on multiple bundle construction benchmarks show that DPE-Rec improves recommendation performance by 63% on average, and its fast variant achieves 25.6$times$ faster inference on average than existing generative recommendation arts, with minimal loss in recommendation quality.
Haonan Dong, Kehan Jiang, Haoran Ye Peking University, Wenhao Zhu, Zhaolu Kang, Guojie Song Peking University
Large Reasoning Models (LRMs) have recently achieved remarkable success in complex reasoning tasks. However, closer scrutiny reveals persistent failure modes compromising performance and cost: I) Intra-step level, marked by calculation or derivation errors; II) Inter-step level, involving oscillation and stagnation; and III) Instance level, causing maladaptive over-thinking. Existing endeavors target isolated levels without unification, while their black-box nature and reliance on RL hinder explainability and controllability. To bridge these gaps, we conduct an in-depth white-box analysis, identifying key neurons (Mixture of Neurons, MoN) and their fluctuation patterns associated with distinct failures. Building upon these insights, we propose NeuReasoner, an explainable, controllable, and unified reasoning framework driven by MoN. Technically, NeuReasoner integrates lightweight MLPs for failure detection with a special token-triggered self-correction mechanism learned via SFT. During inference, special tokens are inserted upon failure detection to actuate controllable remedial behaviors. Extensive evaluations across six benchmarks, six backbone models (8B 70B) against nine competitive baselines, demonstrate that NeuReasoner achieves performance gains of up to 27.0% while reducing token consumption by 19.6% 63.3%.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Kehan Jiang, Haonan Dong, Zhaolu Kang, Zhengzhou Zhu Peking University, Guojie Song Peking University
Recent Large Reasoning Models (LRMs) like DeepSeek-R1 have demonstrated remarkable success in complex reasoning tasks, exhibiting human-like patterns in exploring multiple alternative solutions. Upon closer inspection, however, we uncover a surprising phenomenon: The First is The Best, where alternative solutions are not merely suboptimal but potentially detrimental. This observation challenges widely accepted test-time scaling laws, leading us to hypothesize that errors within the reasoning path scale concurrently with test time. Through comprehensive empirical analysis, we characterize errors as a forest-structured Forest of Errors (FoE) and conclude that FoE makes the First the Best, which is underpinned by rigorous theoretical analysis. Leveraging these insights, we propose RED, a self-guided efficient reasoning framework comprising two components: I) Refining First, which suppresses FoE growth in the first solution; and II) Discarding Subs, which prunes subsequent FoE via dual-consistency. Extensive experiments across five benchmarks and six backbone models demonstrate that RED outperforms eight competitive baselines, achieving performance gains of up to 19.0% while reducing token consumption by 37.7% 70.4%. Moreover, comparative experiments on FoE metrics shed light on how RED achieves effectiveness.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Puzhen Zhang, Xuyang Chen, Yu Feng Hochschule Mainz - University of Applied Sciences, Yuhan Jiang, Liqiu Meng
Given a map description through global traversal navigation instructions, an LLM can often infer the implicit spatial layout and answer user queries by providing shortest paths. However, such context-dependent querying becomes incapable as environments grow larger, motivating the need for incremental map construction that builds a complete topological graph from stepwise observations. We propose a framework for LLM-driven construction and map repair, designed to detect, localize, and correct structural inconsistencies in incrementally constructed navigation graphs. Central to our method is the Version Control, which records the full history of graph edits and their source observations, enabling fine-grained rollback, conflict tracing, and repair evaluation. We further introduce an Edge Impact Score to prioritize minimal-cost repairs based on structural reachability, path usage, and conflict propagation. To properly evaluate our approach, we create a refined version of the MANGO benchmark dataset by systematically removing non-topological actions and inherent structural conflicts, providing a cleaner testbed for LLM-driven construction and map repair. Our approach significantly improves map correctness and robustness, especially in scenarios with entangled or chained inconsistencies. Our results highlight the importance of introspective, history-aware repair mechanisms for maintaining coherent spatial memory in LLM agents.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Keyu Li, Junhao Shi, Yang Xiao, Mohan Jiang, Jie Sun, Yunze Wu, Dayuan Fu, Shijie Xia Shanghai Jiaotong University 等 14 位作者
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture long-horizon real-world scenarios. Moreover, the reliance on human-in-the-loop feedback for realistic tasks creates a scalability bottleneck, hindering automated rollout collection and evaluation. To bridge this gap, we introduce AgencyBench, a comprehensive benchmark derived from daily AI usage, evaluating 6 core agentic capabilities across 32 real-world scenarios, comprising 138 tasks with specific queries, deliverables, and rubrics. These scenarios require an average of 90 tool calls, 1 million tokens, and hours of execution time to resolve. To enable automated evaluation, we employ a user simulation agent to provide iterative feedback, and a Docker sandbox to conduct visual and functional rubric-based assessment. Experiments reveal that closed-source models significantly outperform open-source models (48.4% vs 32.1%). Further analysis reveals significant disparities across models in resource efficiency, feedback-driven self-correction, and specific tool-use preferences.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zhuoqun Li, Xuanang Chen, Hongyu Lin Institute of Software, Chinese Academy of Sciences, Yaojie Lu Institute of Software, Chinese Academy of Sciences, Xianpei Han Institute of Software, CAS, Shanshan Jiang, Bin Dong Ricoh Software Research Center Beijing Co., Ltd., Le Sun Institute of Software, Chinese Academy of Sciences
As researchers delve more deeply into their work, paper search requirements may become more flexible, sometimes involving specific details such as module configuration rather than being limited to coarse-grained topics. However, previous paper search systems are unable to meet these flexible-grained requirements, as previous systems mainly collect paper abstract to construct corpus index, which lacks detailed information to support retrieval by some finer-grained queries. In this work, we propose PaperRegister, which transforms traditional abstract-based index into a hierarchical index tree, thereby supporting queries at flexible granularity. Experiments on paper search tasks across a range of granularity demonstrate that PaperRegister achieves the SOTA performance, and particularly excels in the fine-grained scenarios, highlighting good potential as an effective solution for flexible-grained paper search in real-world applications.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Jianwen Luo, Yiming Huang, Jinxiang Meng University of the Chinese Academy of Sciences, Fangyu Lei, Shizhu He Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Xiao Liu Microsoft Research Asia, Shanshan Jiang, Bin Dong Ricoh Software Research Center Beijing Co., Ltd. 等 10 位作者
Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-task settings. To address these challenges, we propose GATE (Graph-based Adaptive Tool Evolution), an adaptive framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios. We evaluate GATE on open-ended tasks (Minecraft), agent-based tasks (TextCraft, DABench), and code generation tasks (MATH, Date, TabMWP). Our results show that GATE achieves up to 4.3× faster milestone completion in Minecraft compared to the previous state-of-the-art method, and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks. Further analysis shows that GATE exhibits strong adaptive evolution capabilities, effectively balancing tool quantity, complexity, and functionality while maintaining high efficiency. Code and data are available at https://github.com/ayanami2003/GATE.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表