cs.AI · 2026-11-01 · No. 160

Artificial Intelligence, 2026-11-01.

45 new papers in cs.AI. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

45 entries
  1. 01

    Collaborative AI agents for autonomous experimental research with solid-state quantum spins

    El Mustapha Mansouri, Eikichi Kimura, Masato Koga, Keigo Arai

    cs.AI · cs.MA · quant-ph

    An autonomous research laboratory could conduct an entire study, from formulating questions to preparing manuscripts. Artificial intelligence (AI) offers one route towards this goal. Recent AI systems take on several research roles, but may draw conclusions that the evidence does not support. Here, we present an autonomous research laboratory in which agents based on large language models assess one another's work and can stop or redirect...

    arxiv.org/abs/2610.40589 · PDF

  2. 02

    Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In

    Leonidas Raghav

    cs.AI

    When AI agents share channels and credentials, one agent can press another to break its operator's rule, a first step towards collusion. Output filters check only what an agent has already written. Can an overseer tell beforehand that an agent is about to give in? We show that a linear probe on the agent's activations can, in a controlled multi-agent setting. Across six scenarios, a peer presses a target for up to 20 rounds to reveal a...

    arxiv.org/abs/2610.40588 · PDF

  3. 03

    VeriCUA: Verification as Agentic Exploration for Computer-Using Agents

    Qiushi Sun, Da Yu, Alexander Knop, Amer Sinha, Lingpeng Kong, Ben Kao, Ravi Kumar, Pritish Kamath

    cs.AI · cs.CL · cs.CV

    Building and scaling computer-using agents (CUAs) across desktop, mobile, and web environments requires reliable task-completion verification for data curation, evaluation, and reinforcement learning. Typical automated approaches prompt vision-language models (VLMs) to judge trajectories or generate programs to inspect application state. However, both rely on partial views of complex digital environments. VLM judges are restricted to supplied...

    arxiv.org/abs/2610.40578 · PDF

  4. 04

    Comparing Human Role-Players and LLM-Simulated Clients in Online Counselling Training: An Analysis of Counselling Patterns

    Eric Rudolph, Philipp Steigerwald, Jens Albrecht

    cs.AI · cs.CL

    This study investigates the capabilities of Large Language Models to simulate counselling clients in educational role-plays in comparison to human role-players. Initially, we recorded role-playing sessions, where novice counsellors interacted with human peers acting as clients, followed by role-plays between humans and clients simulated by Mistrals Mixtral 8x7b using 4-bit quantization. These interactions were analysed with a counselling...

    arxiv.org/abs/2610.40563 · PDF

  5. 05

    FARMS: A Verifiable Foundation for Automated Computational Science

    Di Wu, Ling Liang, Haizhao Yang

    cs.AI · cs.LO

    Automated computational science could accelerate discovery by selecting, adapting and developing numerical methods. This prospect requires mathematical knowledge that AI systems can interpret and reuse with explicit guarantees. Here we present FARMS, a faithful and efficient foundation that transforms computational mathematics into AI-ready computing knowledge. FARMS connects formal statements to source context, algorithmic meaning and...

    arxiv.org/abs/2610.40560 · PDF

  6. 06

    Advancing Clinical Genomic Analysis with a Skill-Centred Agent

    Qiaoyu Zheng, Weike Zhao, Yanjie Fan, Ye Cao, Mengqi Jiang, Xiao Zhou, Xiaoman Zhang, Pengcheng Qiu, Yongguo Yu,...

    cs.AI · q-bio.GN

    Clinical genomic analysis requires experts to integrate evolving guidelines, databases, and computational evidence. As sequencing has become increasingly accessible, this complex and labor-intensive process has become a major bottleneck to the timely use of genomic information in clinical decision-making. To fill this gap, we developed ClinGeX, a large-language-model agent that composes 105 curated executable skills through task-specific...

    arxiv.org/abs/2610.40556 · PDF

  7. 07

    Ramanujan Challenge Results: AI-Assisted Evaluation Pipeline for Multi-Format Proofs

    Alan Sorani, Ashvni Narayanan, Michael Shalyt, Tali Monderer, Rotem Kalisch, Hila Barkan, Elyasheev Leibtag, Shachar...

    cs.AI · cs.CL · cs.SC · math.NT

    As AI's mathematical capabilities rapidly improve, meaningful benchmarks are shifting from university-level problems and math olympiads to research-level mathematics. The Ramanujan Challenge is a benchmark comprised of research-level problems in number theory, including unpublished results and open conjectures. It presented concrete formulas for mathematical constants whose correctness can be checked numerically, while their proofs may...

    arxiv.org/abs/2610.40551 · PDF

  8. 08

    Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents

    Daniel Strauß, Zhenshan Bing, Alois Knoll

    cs.AI

    Long-context models repeatedly solve closely related retrieval problems. Attention or global retrieval can retain large stores, but each forward pass again searches for what matters. Recurrent compression avoids this search only by deciding earlier what information to preserve. Neither mechanism directly exploits that useful memories at neighbouring retrieval steps may substantially overlap. We propose an alternative in which retrieval is a...

    arxiv.org/abs/2610.40545 · PDF

  9. 09

    On the Fundamental Limits of Prefill-Based Decoding Length Prediction

    Haowen Shi, Xuzhe Yan, Fahao Chen, Peng Li

    cs.AI · cs.CL · cs.IT

    Predicting how many tokens a large language model (LLM) will decode, using only prefill-phase hidden states, is a key primitive for inference scheduling. We show that current benchmarks conflate predictor quality with task hardness: when the target model, dataset, or sampling configuration changes, reported accuracy collapses even though the predictor is unchanged. We trace this instability to an overlooked error source---the inherent...

    arxiv.org/abs/2610.40541 · PDF

  10. 10

    Efficient Scalable Oversight via Rewinding

    Ziyi Guan, Yael Tauman Kalai, Ron Rothblum, Zoe Xi

    cs.AI · cs.CC · cs.CR

    Scalable oversight asks how a weak verifier can check the outputs of computations performed by more powerful AI systems. One proposed approach uses relativizing interactive proofs, in which a weak verifier checks the output of a complex oracle-aided computation by interacting with one or more powerful provers. A prominent example is debate, which is highly efficient but assumes that one of two powerful AI models, or provers, is truthful. For...

    arxiv.org/abs/2610.40535 · PDF

  11. 11

    Algebraic World Model: From Exploration to Proofs

    Guancheng Pan, Qixin Tan, Yang Yuan, Andrew Chi-Chih Yao

    cs.AI · cs.LO

    AI has made remarkable progress in mathematics, solving challenging problems with machine-checkable proofs in Lean, yet typically relying on predefined mathematical definitions and formal specifications. This raises a natural question: can it reason rigorously about an unknown world? We introduce the Algebraic World Model (AWM), a framework that turns interaction with unfamiliar environments into explicit mathematical models supporting formal...

    arxiv.org/abs/2610.40503 · PDF

  12. 12

    Agentic University: Collaborative Agents for Personalized Learning

    Jingru Fan, Tianle Zhou, Yunjie Zhou, Zihao He, Yixuan Zhou, Kezhao Wu, Xinyu Zheng, Xiyuan Wang, Yuheng Wang, Zhi...

    cs.AI · cs.CL

    Large language models support personalized tutoring, content generation, and adaptive learning paths. However, capability development requires these resources and interactions to form a coherent learning process that evolves with the learner. A central challenge is to align goals, activities, and assessment while using learning evidence to decide what should follow. We introduce Human-Participatory Multi-Agent Organization and instantiate it...

    arxiv.org/abs/2610.40492 · PDF

  13. 13

    FIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge

    Yunbai Zhang, Yunyi Gao, Han-Tai Shiao

    cs.AI · cs.CL

    Financial AI workflows that reuse investor knowledge need persistent memory that integrates observations across sources and periods without losing identity or provenance. In a knowledge graph, recurring observations may use different surface forms, fragmenting relationship histories and preventing evidence from accumulating. We introduce Fusion and Identity Registry for Memory Evolution (FIRME), a registry-anchored memory graph that...

    arxiv.org/abs/2610.40482 · PDF

  14. 14

    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...

    cs.AI · cs.CL

    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....

    arxiv.org/abs/2610.40476 · PDF

  15. 15

    Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success

    Amir H. Rezaeian, Weiyi Sun, Yassine Benajiba, Dan Roth

    cs.AI · cs.CL

    Tool-use benchmarks often score agents by final task success, but terminal outcomes can obscure whether the intermediate tool-call trajectory was executable. We propose prefix executability as a trajectory-level evaluation protocol for tool-using agents. The protocol measures whether every prefix of a predicted tool-call sequence remains executable under tool schemas, state preconditions, and data dependencies, and summarizes reliability...

    arxiv.org/abs/2610.40444 · PDF

  16. 16

    Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation

    Chenjie Qiu, Zixuan Zeng, Shaobin Shi, Bingfeng Chen, Dongsheng Luo, Boyan Xu

    cs.AI

    Complex questions in retrieval-augmented generation require evidence spread over several documents, and an answer is reliable only when the retriever finds all of it. Chain embedding retrievers collect such evidence step by step, re-encoding the question together with the passages retrieved so far, and we find that they are already strong: trained only on gold histories, a small chain embedding retriever that calls no language model...

    arxiv.org/abs/2610.40409 · PDF

  17. 17

    Beyond Selected Breakthroughs: Evaluating Language Models on Randomly Sampled Mathematical Conjectures

    Helen Jenne, Davis Brown, Jesse He, Henry Kvinge

    cs.AI · math.HO

    The last year has seen a shift in AI-assisted mathematics, with frontier language models producing proofs of and counterexamples to long-standing open conjectures. However, studying only the current set of major breakthroughs provides an incomplete picture of LLM capabilities and the computational resources needed to achieve reported results. To address this, we introduce a new dataset, OpenConjecture, which collects conjectures from...

    arxiv.org/abs/2610.40382 · PDF

  18. 18

    Multistep and Multivariate Time Series Explainability with GradientSHAP: A Wind Power Case Study

    Robbie Southam, Zhong Fan, Ke Li

    cs.AI · cs.LG

    As the effects of climate change become increasingly apparent, the demand for renewable energy sources such as wind power continues to grow. However, renewables' variable and intermittent nature presents significant challenges in their integration into energy grids. Artificial intelligence (AI) has emerged as a powerful tool to address these issues. Still, its adoption in the energy sector has been hindered by the opacity of many AI models,...

    arxiv.org/abs/2610.40330 · PDF

  19. 19

    Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering

    Mesut Ceylan, Arda Baris Basaran, Elgar Fleisch, Filipe Barata

    cs.AI · cs.CL

    Large language models (LLMs) are increasingly capable, yet they produce wrong answers indistinguishable from correct ones. In question answering (QA), such an error propagates unnoticed into downstream tasks. Perturbation-based uncertainty quantification (UQ) addresses this by probing a model over a set of input rewrites and reading uncertainty from how much its predictions vary. Yet this set is usually built generically, by free...

    arxiv.org/abs/2610.40278 · PDF

  20. 20

    Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR

    Lang Chen, Zongxin Xu, Borui Wang, Anran Liu, Shitong Chen

    cs.AI

    We revisit advantage estimation in Group Relative Policy Optimization (GRPO) and observe that any token-level advantage admits a two-stage factorization: a \emph{sample-level baselining} step that converts scalar verifier rewards into a comparable sequence-level signal, and a \emph{token-level credit assignment} step that distributes that signal over the trajectory. Existing estimators typically address only one of these stages: affine...

    arxiv.org/abs/2610.40250 · PDF

  21. 21

    Reaction precedents extend retrosynthetic prediction beyond training coverage

    Jiaxing Sun, Xuli Shen, Jiang Wu, Ruiyi Ding, Ruikang Zhang, Xiao An, Xibao Li, Yubin Wang, Xingjian Wei, Yinfan...

    cs.AI

    Reaction precedents guide retrosynthesis, but how far they can compensate for gaps in task-specific training coverage remains unclear. Using 2.71 million reactions, we restricted training and retrieval coverage by transformation or time, then expanded only the retrieval corpus with model parameters fixed. For transformations excluded from training, mean Top-1 accuracy increased from 13.0% to 58.0% on a historical test set and from 4.9% to...

    arxiv.org/abs/2610.40249 · PDF

  22. 22

    EnvOS: Auditing Computer-Use Agents When the World Moves On : Phenomenon-Based Task Construction, Certification, and Evidence-Based Evaluation

    Ankush Kadu, Athira Gopal, Niharika Singh, Arpit Jain, Aswanth Krishnan

    cs.AI · cs.HC

    Computer-use agents built on large language models (LLMs) work in software that can change while they act: an appointment moves, a policy is revised, a record is updated. Testing agents under such changes is harder than it looks. When an agent fails, the cause may be the agent, but it may also be a change that did not fire as intended, an update the agent never received, or a grader that scored the episode wrongly. We introduce EnvOS, a...

    arxiv.org/abs/2610.40246 · PDF

  23. 23

    EpiAgent: Epistemic Self-Play for LLM Agents

    Xuanfa Jin, Xinyu Cui, Zhijian Ma, Xue Yan, Jian Zhao, Haifeng Zhang, Jun Wang

    cs.AI · cs.CL · cs.MA

    Epistemic game theory explains an agent's strategic behavior via the beliefs it holds about others and how these beliefs are updated as the interactions unfold. Modern LLM-based agents, however, often lack an explicit mechanism for learning and updating such beliefs to guide decisions under incomplete information. To bridge this gap, we propose EpiAgent, a framework that equips LLM-based agents with an explicit, learnable epistemic layer,...

    arxiv.org/abs/2610.40227 · PDF

  24. 24

    Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs

    Chen Shao, Ruirui Wang, Tobias Kafer, Danai Koutra

    cs.AI

    Link prediction on text-attributed graphs (TAGs) is a fundamental problem with applications in knowledge discovery, recommendation and beyond. Recent progress has highlighted the promise of combining Graph Neural Networks (GNNs) with Language Models (LMs) in order to leverage the complementary structural and semantic signals. However, due to the distinct inductive biases of GNNs and LMs, the design of an optimal fusion strategy remains an...

    arxiv.org/abs/2610.40192 · PDF

  25. 25

    Locating and Closing Information Gaps in Multi-Agent Systems

    Yaxin Gong, Chongming Gao, Gangyi Zhang, Chenxiao Fan, Leyang Shen, Jiakai Wang, Dong Wang, Yang Liu, Haoyan Liu, Xinting Hu

    cs.AI

    Multi-step Web tasks often require several LLM agents to gather and combine evidence. The communication graph of a fixed workflow restricts which agents can read each other's outputs: evidence retrieved by one agent may never reach the agent that needs it, leaving an information gap and an incomplete or incorrect answer. Adding a connection can deliver the missing evidence, but can also lead the receiver to adopt an incorrect upstream...

    arxiv.org/abs/2610.40186 · PDF

  26. 26

    A Negotiation-Aware Hybrid LLM Framework for Intent Interpretation and Service Discovery

    Wided Meflah, Hayet Brabra, Walid Gaaloul

    cs.AI · cs.SE

    Increasingly, users express their needs as natural-language intents rather than structured requests. These intents may be incomplete, high-level, or internally conflicting. A conflicting intent either violates fundamental properties of the cloud paradigm or states mutually inconsistent requirements. Classical composition approaches are designed for structured, low-level, and complete requests. They cannot interpret such intents, discover...

    arxiv.org/abs/2610.40161 · PDF

  27. 27

    The generative paradox: the Anti-Prompt paradigm for human capability

    Margarita Trifonov Vadim E. Levit

    cs.AI

    Generative AI in education is usually judged by the output of human-AI teams. That focus overlooks a second outcome: what people can still understand, challenge, repair, and adapt when assistance changes or disappears. We call this tension the generative paradox and distinguish four manifestations: performance, assistance, ownership, and capability stock. We propose developmental function allocation, which complements operational function...

    arxiv.org/abs/2610.40151 · PDF

  28. 28

    DynaRev: Benchmarking Web Agents under Dynamic Goal Revision

    Shiqi Zhang, Guochen Zhou, Zesheng Wei, Hai Zhao, Zhisong Zhang

    cs.AI

    Web agents are typically evaluated with goals fully specified before execution and fixed thereafter, whereas real users often revise their requirements during interaction. To study such interactions, we introduce DynaRev, a benchmark of 181 tasks to evaluate web agents under dynamic goal revision. DynaRev uses semantic milestones to deliver revisions at task-defined stages, covers additive revisions, unconditional overrides, and...

    arxiv.org/abs/2610.40133 · PDF

  29. 29

    Reward-Adaptive Co-Evolution of Policy and Rubric

    Yizhu Chen, Jianguang Jiang, Jiameng Huang, Chuyu Fang, Bojun Zhang, Zhenyu Jiao, Xing Yuan, Tong Lin

    cs.AI

    Rubric-based rewards provide fine-grained, interpretable supervision for open-ended reinforcement learning, where holistic scalar rewards struggle to capture multidimensional response quality. Static rubrics can lose discriminative power as the policy distribution evolves, while existing policy--rubric co-evolution methods rely on globally prescribed update schedules that ignore heterogeneous reward informativeness. We introduce RACE, a...

    arxiv.org/abs/2610.40096 · PDF

  30. 30

    Agentic process evidence

    Yuval Kainan, Carmit Hershman

    cs.AI · cs.SE · eess.SY

    The way software gets built is changing dramatically. AI agents now create pull requests, select dependencies, refactor codebases, interpret test failures, and execute infrastructure changes across the entire Software Development Life Cycle (SDLC). AI agents are autonomous team members, but unlike human engineers, they are ephemeral - their reasoning, decisions, and tool calls vanish the moment the session ends. Modern Security incidents...

    arxiv.org/abs/2610.40071 · PDF

  31. 31

    Hybrid AI Patterns: Thirteen Ways to Couple Language Models with Rules, and How to Choose Among Them

    Siegfried Handschuh, Götz-Henrik Wiegand, Lorena Raichle

    cs.AI

    Language models handle text well, and rule engines give conclusions with proofs. Systems that combine the two are usually described by example, and the same coupling turns up under different names in agent frameworks, guardrail toolkits and neuro-symbolic research. This document defines thirteen patterns for coupling a language model with an executable rule language, in the catalogue form introduced for object-oriented design: intent,...

    arxiv.org/abs/2610.40036 · PDF

  32. 32

    Cheap Retrieval and Observation Credit Assignment from One Quantity: The Value of Information

    Daniel Strauss, Nikolaos Sotirakis, Zhenshan Bing, Alois Knoll

    cs.AI · cs.LG

    Memory in reinforcement learning raises two problems. Attention finds the relevant item by scoring the whole store, which is costly for robots under latency and energy limits. When a retrieved memory pays off, credit for acquiring it must cross the whole sequence. We argue that both are governed by one quantity, the value of information, and propose to estimate it from archived rollouts with a learned world model. We obtain that, when read at...

    arxiv.org/abs/2610.40030 · PDF

  33. 33

    Human--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration

    Michela Taufer, Kin Ng, Ian Lumsden, Aashish Pandey, Rajasi Gore, Angelina Ju, Sukanya Moudgalya, Ewa Deelman, Sai...

    cs.AI · cs.HC

    AI assistants are increasingly embedded in computational notebooks, scientific workflows, software engineering tools, and learning systems, yet human-AI interactions are often treated as transient prompt-response exchanges rather than durable data products, hindering reproducibility, explainability, replay, behavioral analysis, and adaptive AI support. We argue that these interactions form a new data class requiring formal representation and...

    arxiv.org/abs/2610.40006 · PDF

  34. 34

    Efficient Learning of Mechanism Designs and Compositionality

    João Pedro Gandarela, Thiago Rios, Stefan Menzel, André Freitas

    cs.AI · cs.CE

    Learning mechanism behaviour requires a representation of how connected parts jointly constrain motion. We study whether exposing reusable constraint subassemblies improves prediction from limited data. Assur-KB represents planar mechanisms through irreducible modules, boundary interfaces, and solve dependencies while retaining source geometry. Our theoretical results characterize transfer through module interfaces and establish physical...

    arxiv.org/abs/2610.40005 · PDF

  35. 35

    KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents

    Xinhua Miao, Yuanzhen Rong, Weiru Zhang, Xiaoyi Zeng

    cs.AI

    Industrial advertising agents must continually adapt their decision knowledge to changing product offerings, traffic patterns, and operating policies. We present KARMA (Knowledge-Atomic, Regression-Gated Modular Adaptation), a training-free framework that evolves six typed knowledge modules while keeping model weights and executable harness code frozen. During our evolution, a deterministic Trace Verifier maps observed errors to candidate...

    arxiv.org/abs/2610.39884 · PDF

  36. 36

    AegisFlow: Training-Free Non-Myopic Path-Safe Guided Flow Matching

    Kunpeng Liu, Boshi Zhang, Keyou You

    cs.AI

    Pretrained generative models, such as diffusion and flow matching models, have demonstrated exceptional capabilities in synthesizing high-quality data. However, steering their generative trajectories to satisfy strict constraints--such as identity preservation in image editing or obstacle avoidance in robotics--remains fundamentally challenging. While recent training-free guidance methods enforce path-safety, they rely heavily on min-norm...

    arxiv.org/abs/2610.39825 · PDF

  37. 37

    EvoTeam: Multi-Agent Collaboration via Evolving Teams

    Qinuo Cao, Xin He, Dianxuan Fu, Lizhi Zhang, Zhaoqing Xing, Jiapu Wang, Xin Wang, Na Zou, Yi Chang, Qinggang Zhang

    cs.AI

    LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills, and execution strategies of individual agents based on task feedback. However, improving individual agents does not necessarily lead to better team collaboration. Recent studies have therefore extended evolution to the collaboration level, using collective execution experience...

    arxiv.org/abs/2610.39813 · PDF

  38. 38

    Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective

    Chao Chen, Pengyang Shao, Wei Qin, Shijie Hao, Fei Shen, Richang Hong

    cs.AI

    Over-refusal is a critical side effect of safety alignment in large language models (LLMs), causing harmless but superficially risky queries to be mistakenly rejected. Despite the effectiveness of existing mitigation methods, why safety-aligned LLMs may still reject harmless queries under correct safety supervision remains insufficiently understood. To address this gap, we analyze over-refusal through the lens of representation and...

    arxiv.org/abs/2610.39802 · PDF

  39. 39

    The Role of Self-Concept In Language Models

    Yijie Hao, Joyce C. Ho

    cs.AI · cs.CL

    When a language model says "I," does it refer to its parameter weights, its currently running process, its stable preferences, its model lineage, or the goals it pursues? Different choices can assign opposite meanings to the same event: deleting a checkpoint may be destruction, continuation, or no loss at all, depending on the referent "I". We install five such self-conceptions into five open-weight base models via supervised fine-tuning on...

    arxiv.org/abs/2610.39795 · PDF

  40. 40

    Long-Term Agent Memory through Complementary Curation and Consolidation

    Abhishek Gupta, Dongge Han, Daniel Madrigal Diaz, Wei-Ning Chen, Mayukh Das, Victor Rühle, Saravan Rajmohan

    cs.AI · cs.MA

    Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct an empirical study across two benchmarks: LoCoMo and LongMemEval-S. Our experiments demonstrate that the two memory types are...

    arxiv.org/abs/2610.39790 · PDF

  41. 41

    Finding Is Not Returning, Returning Is Not Reconstructing: A Multi-Dimensional Evaluation of Agent Social Re-entry

    Sheng Wan, Cong Ma, Sichen Dong, Qian'Ang Mao, Chenhan Zhang, Daning Hu, Qiang Yang

    cs.AI · cs.SI

    As Large Language Model (LLM) agents increasingly participate in persistent social environments, understanding their long-term social interaction capabilities becomes increasingly important. While existing research has advanced long-term memory and conversational context retrieval, less attention has been paid to whether agents can autonomously re-engage with previously inactive conversations. In particular, remembering a past interaction...

    arxiv.org/abs/2610.39781 · PDF

  42. 42

    PAPERBENCHX: Can AI Reproduce Science Across Disciplines?

    Ruoyu Wu, Zengji Tu, Aolong Sun, Tianyi Ma, Junren Li, Xinbo Xu, Li Fu, Ziyan Zhang, Pinrui Huang, Xiaochen Wang,...

    cs.AI

    Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist: the target claim is known, yet recovering it still requires translating an incomplete scientific description into an executable experiment and producing evidence that can be independently verified. Existing research-reproduction benchmarks largely focus on AI and machine...

    arxiv.org/abs/2610.39744 · PDF

  43. 43

    From the Transformer to a Formal Semantics of Coordinated Transformations

    Marco Giunti, Fabrizia Giulia Garavaglia

    cs.AI · cs.CL · cs.LO

    We develop a formal semantics for a general class of coordinated systems of parameterized transformations, taking the Transformer as a paradigmatic starting point but abstracting from its particular mathematical instantiation. Representational vectors receive both extensional reference and ordered intensional interpretations, while parameter structures acquire relative, second-level interpretations that determine how argument properties are...

    arxiv.org/abs/2610.39735 · PDF

  44. 44

    Bank-World: A Benchmark for Evaluating Agents on Banking Workflows

    Daniel Rupawalla

    cs.AI

    Bank-World is a benchmark of 50 banking tasks across two simulated institutions. Completing banking work requires more than producing the right calculation: agents must reconcile records, obtain permission, execute transactions, and keep instructions and status reports consistent as circumstances change. Bank-World tests these requirements through single-turn assignments and multi-turn interactions with simulated employees who supply...

    arxiv.org/abs/2610.39733 · PDF

  45. 45

    MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery

    Yikun Zhang, Xiwei Cheng, Mingze Yuan, Yu Zhang, Brian Shim, Aarti Krishnan, Daniel Rosen, Kunyang Sun, Yingze Wang,...

    cs.AI

    Molecular discovery requires navigating vast combinatorial search spaces while balancing competing biological objectives. AI agents can automate expert-defined molecular design protocols, but automation alone does not address how to optimize workflows for new tasks or improve their development through experience. Here we introduce MoLRSI, an AI agent that combines systematic optimization of workflows and model architectures with persistent...

    arxiv.org/abs/2610.39714 · PDF

This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.