cs.AI · 2026-10-08 · No. 137
Artificial Intelligence, 2026-10-08.
32 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
32 entries-
01
RoboJEPA: Scaling Robotic Latent World Models
Artem Zholus, Nicolas Beltran-Velez, Jianhao Yuan, Sarath Chandar, Tushar Nagarajan, Daniel Severo, Koustuv Sinha,...
cs.AI · cs.RO
Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open problem that slows progress in the field. In this work we present RoboJEPA, a world model based on the Joint Embedding Predictive Architecture (JEPA) and trained on a large-scale dataset spanning 12 robotic...
-
02
SciExam for ENSO: Can AI Agents Build Climate Models?
Yinling Zhang, Langchen Liu, Dongbin Xiu, Xueyan Zou, Xu Kuang, Mengdi Wang, Shilong Liu
cs.AI · cs.LG · physics.ao-ph
Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer, a rubric, or a language-model reviewer, none of which can tell whether a new scientific model is valid. The AI Science Exam for El Nino-Southern Oscillation (SciExam for ENSO) is a benchmark in which agents build low-order stochastic models of ENSO, the dominant mode of interannual climate...
-
03
RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
Yilun Hao, Krishna Sayana, Isabella Ye, James S Ren, Sukhdeep Sodhi, Craig Boutilier, Chuchu Fan
cs.AI
Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieval, while agentic variants adapt queries and tool use but remain largely retrieval-centric. However, in many tasks, the evidence required for a solution is not explicitly present in any single source item. Instead, it must be derived through...
-
04
Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models
Daniel Robert Kling Alexander, Catherine Louise Kling
cs.AI · cs.CL · econ.GN
Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh competing values. Stated-preference economics has faced this problem for decades. It judges survey responses without knowing the true value, through a framework of validity and related concepts: content, construct, and criterion validity, reliability, incentive compatibility,...
-
05
EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
Python Song, Zhixuan Liang, Kelsey Fu, Mengdi Wang, Junfeng Yang, Shilong Liu
cs.AI
Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt around the model, but current self-evolving harnesses use robot trials inefficiently when deciding which code and skill changes...
-
06
Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
Tan Yu, Alexander Bukharin, Khushi Bhardwaj, Jennifer Williams, Zirui Liu, Jonathan Lingjie Li, Soumye Singhal,...
cs.AI · cs.SE
How can we predict which base checkpoint is worth an expensive round of agentic post-training? End-to-end pass@$K$ tests whether successful behavior already appears in a base model's distribution, but it is a poor fit for agentic coding: many base checkpoints cannot reliably produce the well-formed tool invocation required to complete a task end-to-end. Single-shot or short-horizon tasks avoid these tool-calling failures by collapsing a...
-
07
RunningTab: Direct Workspace Interaction with Environment-Side Tabs
Jinheon Baek, Soyeong Jeong, Yumin Choi, Dongsu Han, Sung Ju Hwang
cs.AI · cs.CL
Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over. Through direct corpus interaction, an agent can search and read any of those files from a terminal with no indexing, and producing a deliverable from many of them in this way is what we call direct workspace interaction (DWI). Reaching the files, however, is only half the task: nothing keeps track of what...
-
08
SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions
Yizhen Xie, Mengyang Liu
cs.AI · cs.LG · q-fin.PM · q-fin.TR
As option markets grow and AI advances, agentic systems for option trading are gaining increasing attention. Language-model-based agents can reason over contextual information such as news, but option trading presents a particularly challenging decision problem: a single stock can have thousands of contracts, and the agent must decide both which contracts to trade and how to combine them. Existing approaches often sidestep this complexity by...
-
09
Reasoning-Token Spikes Under Prompted Untruthful Responding in Large Language Models
Maverick Morales, Tomáš Dominik, Vermut Gao, Katrina Shirey, Paulius Rimkevičius, Aaron Schurger, Uri Maoz
cs.AI · cs.CL
Monitoring the chain-of-thought of reasoning artificial intelligence (AI) models remains a key approach to detecting deception and other forms of misbehavior in such models. However, semantic chain-of-thought monitoring depends on reasoning traces being legible and sufficiently faithful to the underlying computations that produced the model's behavior, not to mention accessible. Moreover, there is increasing evidence that chain-of-thought...
-
10
Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning
Junkai Chen, Yuhao He, Qianshan Wei, Junxiang You, Jingwen Shao, Junkai Lin, Zhongkai Yue, Xiaotian Ye, Zhengbo...
cs.AI
As multimodal large language models (MLLMs) become more capable and widely deployed, concerns about privacy and safety have become increasingly pressing. Machine unlearning offers one approach to addressing these concerns by removing designated information from trained models while preserving unrelated capabilities. However, fragmented implementations and evaluation protocols, incomplete robustness testing, and limited understanding of metric...
-
11
The Handover Problem: Governing Autonomy Transitions in Human-AI Collaboration
Vicente Pelechano, Antoni Mestre, Manoli Albert, Miriam Gil
cs.AI · cs.HC
Human-machine systems rarely operate at a fixed level of AI autonomy. As operators and AI systems collaborate over time, control must shift: the AI can take on more responsibility when collaboration is stable, maintain its current role when evidence is ambiguous, or return control to the human when conditions deteriorate. Existing work on adaptive automation, supervisory control, trust in automation, and deskilling explains parts of this...
-
12
AI Safety Considerations for Agents With Limited Time to Act
Leo Zeitler, Jack Richings, Victoria Nockles
cs.AI · cs.LG
In the wake of the increasingly public discussion about AI alignment, recent work has tried to propose specific AI architectures that behave safely. However, the proposed arguments that seemingly demonstrate proved alignment mostly neglect the environment the agent needs to act in. We discuss theoretical bounds for agent-agnostic safety guarantees in environments that can only be partially observed and within which an action is required...
-
13
Stale, Misattributed, or Late: Where Personal Memory Fails Before Generation
Haonan Deng, Park Sinchaisri
cs.AI
Personal memory for language agents is usually judged by whether the final an- swer is correct. That score hides errors that arise before generation: the memory block may contain an obsolete value, a fact about the wrong person, or no use- ful fact before the serving deadline. We measure these failures directly. Using Personal Fact Memory (PFM) as a reference layer, we find that temporal validity is primarily a property of memory construction...
-
14
OOM-RL II: Reality Is an Oracle, Not a Debugger Provenance-Constrained Diagnosis in Continually Evolving Agent-Engineered Systems
Kun Liu, Liqun Chen
cs.AI · cs.SE · q-fin.PM
Reality may establish that an outcome occurred without identifying which evolving procedure produced it or why. This distinction matters in production ML systems whose code, configuration, and artifacts change while external feedback accumulates. We examine it in a human-directed, agent-engineered quantitative trading system, using oracle to mean an external source of realized outcomes rather than a complete correctness specification. Across...
-
15
GAGR-Lab: Evaluating Joint Spatial-Geometric and Analytic Function Reasoning
Jingyao Zhang, Yun Li, Lu Han
cs.AI · cs.CL · cs.CV · cs.LG
Joint spatial-geometric and analytic function reasoning requires translating a perceived spatial configuration into a symbolic function whose executed curve satisfies geometric constraints. We present GAGR-Lab, a framework for measuring this capability through Cartesian game scenes, explicit function semantics, and authoritative Rust trajectory execution. It distinguishes spatial perception, metric grounding, geometric relations, function...
-
16
Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint Programming
Ángel Sánchez-Fernández, Javier Pernas-Álvarez, Diego Crespo-Pereira
cs.AI · cs.SE
Developing optimization models for production scheduling requires substantial expert effort. Research on large language models (LLMs) has followed two directions: specialized approaches for automated modeling, mostly for mixed-integer linear programming, which often rely on dedicated training or problem-specific architectures that limit industrial deployment; and agentic artificial intelligence for operational decision support, which...
-
17
UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
Yifei Lu, Cheng Liu, Dianzhi Yu, Hui Xiang, Ji Zhang, Yuanchu Xiao, Rong Liang
cs.AI
Large language model agents can improve across tasks by retaining reusable skills distilled from prior interactions. Recent work jointly optimizes task execution and skill extraction, enabling the policy and skillbank to co-evolve. However, as the actor continues learning, rewarding skill proposals through their reuse in subsequent training steps may conflate skill benefits with actor improvement, while directly testing each proposed skill...
-
18
RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation
Hengbo Xiao, Boyao Zhang, Purui Liu, Yuxuan Zheng, Haoran Yin, Haibo Liu, Fan Zhang
cs.AI
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in domains where task outcomes can be reliably evaluated, but long-horizon interaction remains challenging due to sparse terminal feedback and difficult credit assignment. Process rewards provide denser supervision, yet the capabilities most relevant for training can change as the policy evolves: a behavior that is easy to evaluate or frequently deficient...
-
19
SkillSandbox: Skill Verification via Dynamic Scenario Synthesis
Serin Kim, Kwangwook Seo, Dokyung Song, Jinyoung Yeo, Dongha Lee
cs.AI · cs.CL
Self-evolving agents distill task-solving experience into skills for future reuse, but these skills can encode incorrect procedures or non-transferable knowledge. It is therefore critical to verify each skill's reusability: whether its guidance remains useful beyond the experience from which it was distilled. Such verification requires observing how a skill affects execution in new tasks, yet existing tasks may not expose the situations where...
-
20
HGP:An on-device personalized agent memory via hybrid graph storage
Ran Zhou, Xueming Han, Jiaheng Liu, Yuyao Zhang, Fanyu Meng, Junlan Feng, Yuxiang Ren
cs.AI
LLM-based agents face challenges in personalized interactive tasks due to heterogeneous, multi-typed, and implicitly constrained long-term traces. Existing memory mechanisms struggle with accurate routing and retrieval, especially on-device where personalization is critical. Most methods use single-vector representations, blurring type distinctions and relational structure. We propose HGP, a hybrid graph memory framework. HGP employs a...
-
21
Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents
Obada Kraishan
cs.AI
Tool-using agents are usually scored on whether they finish a task while the tools work. Deployments are less forgiving: services time out, endpoints disappear, parameter names change, and results come back well formed but wrong. Prior work has shown that language models over-trust tool outputs that fail silently; we ask how that over-trust plays out across the stages of failure handling in multi-turn agents. Wrapping the executable...
-
22
Learning to Accumulate Knowledge with Mutual Information
Yuyang Zhao, Lizi Liao, Leyang Shen, Xiaoyan Zhao, Yang Zhang, Fuli Feng, Xiangnan He
cs.AI
Large language model (LLM) agents can improve their performance by reusing knowledge distilled from past interactions. However, curating new experiences into a knowledge bank that becomes more useful as it grows remains challenging. Effective knowledge accumulation should limit redundant overlap among entries and ensure that new knowledge contributes beyond what the bank already provides. Yet training a curator with Group Relative Policy...
-
23
What the Sleeve Feels: Explainable Machine Learning for Textile Pressure-Based Postural Screening
Limon Bin Hossain, Md Sadib Rahman Ananta
cs.AI
Pressure-sensing smart textiles convert body-surface contact into a dense, image-like signal closely tied to posture and movement, making them a promising low-cost route to wearable posture screening. Realizing that promise, however, requires more than classification accuracy: a deployable system must generalize to wearers unseen during training, expose the physical evidence behind its decisions, and tolerate the small donning offsets that...
-
24
From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM Agents
Juanyang Xu, Zheng Wang, Xingyu Zhao, Siddartha Khastgir, Andi Zhang
cs.AI
When the harmfulness of an LLM agent's output can be quantified, a natural jailbreaking objective is to maximize expected harmfulness over admissible input modifications. An alternative approach constructs or selects harmful target outputs and modifies the input to increase their likelihood. We establish a precise connection between these two approaches through a probabilistic reformulation. Specifically, we show that the gradient of the...
-
25
Successive Training Stages and Large Language Model Persuasion: Effects of Misalignment, Supervised Fine-Tuning, and Preference Optimization
Antony Dalmiere, Pascal Marchand, Guillaume Auriol, Vincent Nicomette
cs.AI · cs.CY
Large language models (LLMs) can be tuned to influence human attitudes, yet the respective contributions of successive post-training stages remain un-clear. This study examines how three successive training stages affect LLM persuasiveness: (1) misalignment through supervised fine-tuning (SFT) on conspiracy data, (2) additional persuasive SFT on argumentative data, and (3) Identity Preference Optimization (IPO), a preference-optimization...
-
26
AgentTime: Can Agents Estimate and Control Their Own Runtime?
Michael Ofengenden, Maksym Andriushchenko
cs.AI
An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-clock time and to control their own actions. Prior work has focused on time-awareness, but duration-following and control in native agent harnesses remain unexplored. We present AgentTime, a benchmark for testing whether agents can work for a requested duration, predict their runtime, and estimate...
-
27
Where Can a Decision Model Diagnose HVAC Faults? Reasoning Demand, Physical Representation, and Robustness Under Shift
Wooyoung Jung
cs.AI
Artificial intelligence supports building operations in several forms, each with its own barrier. Expert rules must be tuned for every system, supervised models need labeled data that buildings rarely record, and language models return free text that requires human-in-the-loop checking, since their stated confidence is unreliable. A newer kind of pretrained model, here called a decision model, returns a probability for every allowed answer,...
-
28
NL2Hull: A Natural Language-Driven Constrained Ship Design Decision Framework
Wenhua Huo, Fenglei Han, Wangyuan Zhao, Jialin Wu, Jiayi Han
cs.AI
Ship-form design combines smooth geometric representation, local shape editing, and constraints on the resulting hull. We present the Natural-Language-to-Hull Framework (NL2Hull Framework), which formulates ship-form editing as a typed discrete decision problem and connects language decisions to numerical geometry. Its Constrained Free-Form Deformation Engine (CFFD Engine) represents hull waterlines with non-uniform rational B-splines...
-
29
Outperformance Inverse Optimization: Learning Objective Functions that Outperform Agent Decisions
Akira Kitaoka
cs.AI · math.OC · math.ST · stat.ML
Inverse optimization estimates the weights of an objective function that explain observed decisions as optimal solutions, and is used in a variety of fields. For mixed-integer linear programs (MILPs), existing methods aim to reproduce the observations as optimal solutions, and thus learn compromise weights when the observations are suboptimal. We propose outperformance inverse optimization, which instead seeks weights that induce, at each...
-
30
Think Before You Paint: Recursive Latent Reasoning for Diffusion Models
Paweł Skierś, Małgorzata Grzanka, Wojciech Masarczyk, Jan-Willem van de Meent, Kamil Deja
cs.AI · cs.LG
Diffusion models generate realistic images but often fail on visual reasoning tasks, such as filling in a Sudoku or drawing the path through a maze. When a discrete symbolic representation is available, recursive methods such as the Tiny Recursive Model (TRM) solve even hard instances of these puzzles. We ask how such reasoning can be carried over to pixels, where no symbolic representation is available. We propose Painter-Thinker (PaTh): a...
-
31
LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets
Jun Zhao, Leiming Fu, Yanbo Wen, Yiding Wang, Xuantong Liu, Yang Shu, Yuyang Lu, Xuanran Xing, Jingqi Tong, Hao Xu,...
cs.AI · cs.CL
Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, where outcomes reflect a closed-loop interaction between agent behavior and changing external conditions. We introduce LiveMACEBench, a process-aware benchmark that uses live financial markets as a naturally evolving testbed for persistent LLM agents. Five frontier LLMs operate along continuous...
-
32
Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents
Wenjie Liao, Liangjie Zhao, Zehong Cao
cs.AI
Self-evolving tool-integrated agents learn from tasks and feedback generated within their own training loop. A Curriculum Agent generates tasks, while an Executor Agent learns from self-consistency signals through reinforcement learning. However, relying solely on the current Executor for feedback has two limitations: group-relative advantages vanish under full consensus, while uncertainty-based curriculum rewards favor disagreement without...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.