cs.AI · 2026-10-14 · No. 143
Artificial Intelligence, 2026-10-14.
42 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
42 entries-
01
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards
Xin Gao, Yifan Yang, Xin Li, Pan Wang, Yan Li, Muzhao Tian, Mingxi Cheng, Bei Liu, Kai Qiu, Qi Dai, Dong Chen, Yue...
cs.AI
Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet code models cannot see how their choices of layout and color come together on the canvas, often limiting spatial planning and aesthetic quality. Image generators excel at visual design but can misrender requested content, making their outputs unreliable targets for direct...
-
02
MFG: Multi-turn Feedback Guided Molecular Optimization
Trieu Nguyen, Frazier N. Baker, Ruoxi Gao, Daniel Adu-Ampratwum, Xia Ning
cs.AI · cs.LG · q-bio.QM
Multi-objective molecular optimization is a critical process in drug discovery that aims to modify a given molecule to simultaneously improve multiple properties while maintaining a similar overall structure. This process often requires iterative modifications guided by computational or experimental feedback. Recent large language model (LLM)-based methods have begun to explore this iterative approach; however, these methods are not...
-
03
Who Improves the Robot? Toward Physical Recursive Self-Improvement
Hai Zhou, Fan Yang, Zeyi Chen, Lejun Zhang, Chenyang Fu, Jianping Li, Jiayi Zhu, Xianyang Liu, Yingxuan Yang, Lili...
cs.AI · cs.LG · cs.RO
Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Self-Improvement (Physical RSI), in which physical experience guides lasting updates to both a robot's capabilities and its improvement procedure, making subsequent improvement more effective across tasks. Physical RSI faces challenges from noisy observations, continuous dynamics, costly trials,...
-
04
Read the Room Before Your Model Generates
Muyao Kong, Zhihao Lin
cs.AI · cs.CL
Large language models (LLMs) generally rely on sampling temperature to regulate the amount of randomness in their outputs. Mainstream methods for selecting temperature typically involve fixed, heuristic global settings and context or token-level calibration, rather than a geometrically interpretable representation of the communicative scenario. In this work, we introduce a simple and interpretable temperature selection framework, the...
-
05
Self-Evolving Agent Harness
Chuyang Wei, Haoxiang Guan, Minghang Zhu, Kexin Zhou, Jiyan He, Xiren Zhou, Huanhuan Chen, Yifei Shen
cs.AI · cs.CL
Harness self-evolution revises an agent's software scaffolding, including prompts, memory, workflows, and executable components, while keeping model weights fixed. We formalize a feedback-driven process in which accepted revisions persist across runs. The framework separates update targets from proposal and admission mechanisms. It distinguishes changes to interpreted state from revisions to tools and code, repository-level control logic, and...
-
06
Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents
Yuchen Lu, Julian McAuley, Lei Zhang
cs.AI · cs.CL
Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved. This raises a natural question: can long-horizon context instead be organized around reusable progress rather than the history that produced it? In this paper, we introduce CarryOn, an object-oriented context runtime that organizes continuation around reusable task objects. Rather than...
-
07
BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems
Xiaoguang Guo, Yaohao Long, Chuxu Zhang
cs.AI · cs.CL
Large language model multi-agent systems extend individual agents' capabilities through collaboration across specialized roles, tools, and workflows. Yet collaboration makes failures harder to diagnose: one agent may misinterpret a correct result while others carry the mistake forward. Failure attribution therefore seeks to identify the responsible agent and decisive error step. Recent methods trace dependencies, but knowing where information...
-
08
Jeva: System One Models from First Principles
Qi Li, Xinchao Wang
cs.AI
System one models enable direct, low-latency decision-making. Yet recent practice of predicting an answer from serialized text does not, by itself, respect the structure of a decision problem. We argue that current designs underemphasize four important structural requirements. (i) null-aware: Models should distinguish answer absence from uncertainty among candidates; (ii) permutation-invariant: Reordering alternatives should not change the...
-
09
Beyond the Verdict: Agentic Code Judging with Verifiable Feedback
Zheye Deng, Sha Li, Changlong Yu, Xin Liu, Qin Lu, Priyanka Nigam, Yangqiu Song
cs.AI
Test-time scaling for large language models (LLMs) can involve generating multiple candidate solutions for selection or revising an earlier attempt. To guide selection and revision, we need a verifier that can estimate candidate correctness and provide evidence of failure. In competitive programming, however, official judging systems provide authoritative verdicts under finite submission budgets, without revealing failure explanations or...
-
10
Unlocking Token Rewards via Training-Free Reward Attribution
Sitong Wu, Haoru Tan, Bin Xia, Xichen Zhang, Jingyao Li, Shaofeng Zhang, Xiaojuan Qi, Bei Yu, Jiaya Jia
cs.AI
In this paper, we propose an extremely efficient, training-free method to extract token-level reward signals directly from an existing deep reward model. Our core idea is to attribute the overall process reward to individual tokens by estimating each token's influence. This influence is defined as the change in the final macroscopic reward (e.g., the process reward) when a token is replaced with a semantically null token. Naively calculating...
-
11
Knowing the User Is Not Knowing What We Established: Grounding Awareness in Personal Agents
Jiajun Chen, Xinyue Chen, Yicheng Jiang, Hua Shen
cs.AI · cs.HC · cs.LG
Personal-agent memory has largely focused on learning what users know, prefer, and want. However, knowing the user does not necessarily mean knowing what the user and the agent have established together. An assistant's proposal should not become an authorized instruction merely because it is remembered. We introduce Grounding Awareness, the ability to distinguish accepted, unacknowledged, revised, and scoped arrangements when selecting...
-
12
To Align or Not To Align: Check Your COMPASS Before You Train
Fabian Gröger, Petar Damjanović, Maria Brbić
cs.AI · cs.CL · cs.LG
Combining pretrained models is a common strategy for building AI systems, whether by aligning a vision encoder with a language model or merging fine-tuned checkpoints. However, finding compatible pairs typically requires costly empirical search, as compatibility is known only after alignment or merging. We propose COMPASS (COMPatibility ASsessment Score), a theoretically motivated diagnostic that estimates whether a model pair will be...
-
13
Two Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference
St John Grimbly, Nicolas Kuske, Evert A. Boonstra, Charel van Hoof, Rowan Hodson, Benjamin Rosman, Ryan Smith, Mark...
cs.AI · q-bio.NC
An embodied agent must prioritise among competing bodily needs. In active inference, it can respond to an urgent need by increasing the precision of information about that need or by increasing its preference for outcomes that relieve it. We compare these two interventions, separately and together, in a foraging gridworld with three lethal needs, and ask how each changes survival, perception and the body model the agent learns. Precision...
-
14
Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents
Ashutosh Hathidara
cs.AI · cs.LG
Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human. That decision needs a per-step confidence signal predicting whether the current rollout will eventually succeed. The agent's own self-reported verbalized confidence is the natural candidate, but existing reinforcement learning methods calibrate it against the correctness of a decision at the...
-
15
Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces
Haotian Liu, Yingjian Chen, Xiaohang Xu, Lang Huang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li
cs.AI · cs.CL
Large language models increasingly tackle tasks that require multi-step reasoning, where errors in intermediate claims can affect the final answer. Self-consistency (SC) improves reasoning by voting over sampled final answers, but its vote leaves intermediate disagreements unresolved. To address this problem, we introduce DDRG (Disagreement-Driven Verification Guided by Reasoning Graphs), a framework for selective correction from a frozen...
-
16
AgentStripes: An Evidence-Graded Maturity Model for AI Agents
Nutan Kumar Naik, Vijay Prasad Poudel, Aditya Kumar Saroj, Saurav Samantray, Abhishek Patel
cs.AI · cs.CY · eess.SY
Benchmarks report what an Artificial Intelligence (AI) agent can do on a task suite, but not whether one released version has been engineered with the controls that make it reliable, safe and observable, or how strongly that is shown. This paper proposes AgentStripes, an evidence-graded maturity model for AI agents. It defines levels (0 to 7 stripes), process areas (12 areas holding 40 capabilities), three gates (basic, safety, proof) that...
-
17
Auditing Future-Memory Use in Point-in-Time Language Agents
Rongtian Ye
cs.AI
Point-in-time (PIT) agents can recall post-cutoff facts even when their external evidence respects a historical cutoff. We examine whether this access predicts evidence gathering in 48 historical company-comparison tasks. Independent closed-book revenue probes identify the better-remembered company for each model on tasks with unequal recall, fixing the predicted direction before agent runs. We then compare paired runs with real or anonymized...
-
18
Compare to Correct: Pairwise-Guided Logit Adjustment for LLM Test-Time Scaling
Cong Hua, Qianqian Xu, Zitai Wang, Zhiyong Yang, Shilong Bao, Linchao Zhang, Qingming Huang
cs.AI
Sampling-based test-time scaling enhances LLM reasoning by aggregating multiple reasoning paths for the same query. Existing methods use answer frequencies or path confidence to compute candidate scores, which do not explicitly characterize comparisons between competing answers. Inspired by the Condorcet principle in social choice theory, we introduce pairwise confidence comparisons between paths supporting different answers to capture...
-
19
Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops
Yubo Li, Ramayya Krishnan, Rema Padman
cs.AI
System One models choose an agent's next action by scoring a supplied set of options in a single pass. This makes them fast and cheap, but when they choose wrongly there is nothing to inspect: did the model misread what the agent has seen, or read it correctly and still act wrongly? We answer behaviorally. On a frozen benchmark of agent decision states from simulated environments, customer-service policies, tool use, web navigation and...
-
20
LLM Agents for Automated Post-Training via Structured Recipe Optimization
Ruohong Liu, Bohan Tang, Lekang Jiang, Jack Umenberger, Yiwen Guo
cs.AI · cs.LG
Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically constructing and optimizing a recipe of coupled decisions over data sources, data processing, cross-domain composition, and training configuration under a limited experimental budget. Existing automation either searches predefined recipe spaces that enable systematic optimization but remain fixed rather...
-
21
Order-Consistent Latent Geometry for Reliable Short-Horizon Planning in World Models
Junlin Wu, Wen Fan, Dandan Zhang
cs.AI
Latent planners often rank candidate action sequences by terminal Euclidean distance to a goal latent. Exact agreement with transition distance would make this score ideal, but is stronger than planning requires: along a transition-shortest rollout, the essential requirement is that latent distance does not reverse true transition progress. We show that this pathwise no-reversal requirement is precisely the classical self-approaching...
-
22
Configuring RAG Systems: What Breaks, Where Originates, and How to Fix
Liangyu Chen, Youpeng Ma, Yulong Ye, Zezhen Xiang, Tao Chen
cs.AI
Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for improving Large Language Model (LLM) by intertwining it with other components, such as a vector/graph database. Therefore, the resulting RAG systems are often highly configurable, under which a non-trivial amount of failures are related to the configurations. However, there remains a lack of systematic understanding regarding the configuration issues for RAG systems....
-
23
Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection
Yichi Zhang, Zhenxiang Huang, Yuyang Zhang, Yuchen Yang
cs.AI · cs.CR
Large language model (LLM) routers reduce serving cost by choosing which model to call and how many output tokens to grant it for each query. Existing routers rank model-budget actions using a single quality metric. This does not work for mixed workloads. For ordinary queries, a good answer is correct and useful (utility); for security-sensitive queries, a good answer refuses harmful requests or resists malicious instructions (security)....
-
24
Input-Conditioned Search for Efficient Test-Time Scaling of Recursive Reasoners
Haochen Shi, Tianwen Fu, Qianggang Ding, Yinhan Lu, Yizhan Li, Huan Zhang, Yajie Zhao, Xingdi Yuan, Hengyang Lu, Bang Liu
cs.AI
People often tackle difficult problems by thinking more deeply or exploring more possibilities. Similarly, recursive reasoners, which reason by repeatedly applying a learned update rule to latent states, can also scale inference through more updates (depth) or additional trajectories generated by perturbing latent states (width). When people hit a dead end in their thinking, they may step back and approach the problem from a fresh angle....
-
25
Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale
Jinlin Liu, Wei Chen, Xiaojin Zhang
cs.AI
Reusable skills let LLM agents load task-specific instructions on demand, but they make execution depend on implicit routing over skill metadata. We test whether this design scales by holding SkillsBench tasks and their golden skills fixed while adding irrelevant skills. We find skill routing collapse: agents increasingly load fewer or no skills, even though the relevant skills remain available. With 1,000 irrelevant skills, loaded-skill...
-
26
The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale
Judah Goldfeder, Ayush Rai, Philippe M. Wyder, Na Li, Victoria Dean, Donna Vakalis, Jiong Lin, Bing Dong, Michael...
cs.AI
Buildings cause nearly 40\% of carbon emissions in the US. Of total building emissions, HVAC systems are responsible for approximately 40-60\% and account for 15\% of global energy consumption. Despite advances in artificial intelligence, most buildings still operate as inefficiently as they did decades ago. Building optimization, perhaps more so than any other optimization problem, has enormous potential for Machine Learning (ML) driven...
-
27
Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments
Linhai Ma, Yan Wang, Lingfei Qian, Yupeng Cao, Victor Gutierrez Basulto
cs.AI · cs.CL
Tool-call judges evaluate argument values proposed by LLM agents. We find that they accept a correct value less often when their input holds no reference for it, that is, no text that says what the value should be. This happens when the value is a default value from the function schema that the user did not mention, when it has to be inferred, or when the text it comes from was cut from the judge input. We call this drop in acceptance the...
-
28
ReTerm: Recovery Training for Self-Improving Terminal Agents
Wei Xie, Kaituo Feng, Shiming Fu, Yong Liu, Xiangyu Yue, Shuangjia Zheng
cs.AI · cs.LG · cs.SE
Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution (e.g., command errors, faulty implementations), eventually leading to task failures. To this end, we present ReTerm, a self-improving terminal agent trained by learning how to recover from its own failed terminal tasks. To support its training, we construct a customized data pipeline and...
-
29
Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery
Yibo Wen, Han Liu
cs.AI
AI agents for autonomous scientific discovery must decide which experiments to run under a limited budget. Most benchmarks for science agents provide fixed datasets, while others that support active experimentation largely rely on simulation. We introduce Autonomous Science Bench, an initial release comprising six budgeted design-build-test-learn campaigns grounded in published experiments across biology, chemistry, and materials science....
-
30
Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence
Thinker Team, Peng Gao, Jichao Jiao, Chen Liao, Daqin Luo, Yiming Ma, Baiyu Pan, Hailin Shi, Jiyuan Wang, Xiangming...
cs.AI · cs.CV · cs.RO
World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the functions they support. In particular, visual dynamics, geometric structure, and executable action are commonly coupled through separate interfaces or downstream modules rather than being jointly represented and evolved within a shared dynamics model. In this work, we present Thinker-WM, a...
-
31
The Singularity Has a Distribution: Exact Timing Laws and Detection Limits for a Stochastic Intelligence Explosion
Xiaoyu Li, Zheng Gao, Chiwun Yang, Zhizhou Sha
cs.AI · cs.CY · math.PR
Automating AI research creates a positive feedback loop between software capability and research effort. We study a stochastic realisation of this loop in which independent, positive, multiplicative improvements arrive at a rate proportional to a power of current capability. Within this model, randomness leaves the deterministic explosion threshold unchanged but replaces the blow-up date by an explicit distribution. For equal-sized...
-
32
Delegating Earth science model calibration to knowledge-guided LLM agents
Zhanliang Zhu, Ziwei Li, Liujun Zhu, Yuchen Liu, Junliang Jin, Jianyun Zhang
cs.AI · cs.CE
Applying process-based Earth science models to new sites and questions often requires expert calibration decisions. Reliable delegation to language-model agents must preserve scientific competence and reproducibility. Here we develop a general calibration harness (GCH) for end-to-end delegation from a calibration request to assessed results. Constrained by a knowledge infrastructure (KI) and a validation convention, agents define parameter...
-
33
ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution
Qiuyu Ding, Heng-Da Xu, Changda Xia, Jiajun Shen, Zihao Guan, Zhengchen Yuan, Jianfang Zhang, Di Yang, Jiayi Tian,...
cs.AI
We introduce \textbf{ABot Embodied Reasoning (ABot-ER)}, a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embodied reasoning. Embodied intelligence demands the joint mastery of perception, planning, and execution, yet reconciling generality with specialization across this spectrum remains an open challenge. Within a single unified model, ABot-ER commands specialist-level depth across all three...
-
34
Choosing LLMs for Strategic Agent Interactions
Arastun Mammadli, Herbert Woisetschläger, Jawad Fayaz, Shiqiang Wang
cs.AI · cs.IR · cs.MA
Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capability dimensions. However, they only evaluate strategic performance across individual fixed models. In parallel, contemporary LLM routers pick models under quality-cost trade-offs, but with no notion of a strategic structure. They do not account for an opponent that might be unknown, and that can...
-
35
AssetForge: Asset-Augmented Task Synthesis for Business Automation Agents
Xiangrui Liu, Shuo Tang, Siheng Chen
cs.AI
Training business automation agents requires executable tasks that connect a natural-language request to an application state and a verifiable end state. Traditional Rubrics requires Authors to recreate application interfaces, initial records, policy evidence, and outcome checks for each task, entangling business logic with repeated infrastructure work. We introduce AssetForge, an asset-augmented task-construction pipeline that pairs a...
-
36
Complex materials engineering via Provenance Action Graphs: potential, structure and demonstration
Yevgeny Rakita, Paul Todd, James R. Neilson, Simon J. L. Billinge
cs.AI · cond-mat.mtrl-sci
This work discusses and tests the potential of reaction graphs for material synthesis, in which events consist of reaction steps (actions) and their outputs (observations). The importance comes from the requirement to synthesize technologically useful materials, especially those that are kinetically stabilized. Often, it is a science that follows years of trial and error, culminating in (published) successful recipes, but is truly driven by...
-
37
Efficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction
Md Asiful Islam, Fahmida Alam, Mihai Surdeanu
cs.AI
Guardrail approaches that rely on reasoning-based large language models (LLM) improve safety decisions, but come with substantial inference overhead due to the explicit reasoning. We introduce LR-Guard (Latent Reasoning Guardrail), an efficient and explainable guardrail that jointly learns structured latent reasoning and on-demand reasoning reconstruction. Our method distills a frozen teacher's analysis of safe and unsafe prompt...
-
38
A dataset of formalised theorem statements from the Annals of Mathematics
Thomas Browning, Katerina Hristova, David Ledvinka, Justus Springer, Hang Lu Su, Jack McKoen, Kevin Buzzard
cs.AI
Recent progress in autoformalisation of mathematics using AI has been impressive. Measuring this progress requires datasets of formal statements that are both hard and trustworthy. We present AnnalsChallenge: 50 formalised theorem statements written by hand in Lean 4 using Mathlib. Each is the main result of a paper published in the Annals of Mathematics since 2020. Every formalisation was manually reviewed and then audited by AI. We release...
-
39
Output Discipline Sets the Floor: A Falsification-Guided, Model-Agnostic Agent Protocol for Auditable Hypothesis-Driven Decision Making
Jing Liu, Yongxing Qi, Ping Yao, Ting Wu
cs.AI
What binds large language models on auditable, hypothesis-driven decision tasks, where every candidate can be checked against the evidence? On the public TCMEval-SDT benchmark for Traditional Chinese Medicine syndrome differentiation (200 cases), the binding constraint is output discipline and reasoning structure, not model capability alone: two years of model scaling move zero-shot scores by only -0.03 to +0.08, while output-discipline...
-
40
Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate
Dezheng Bao, Sihang Du, Renhong Huang, Zhizhang Yuan, Yifei Sun, Yang Yang
cs.AI
Multi-agent debate (MAD) aims to improve large language model reasoning by exposing agents to alternative solutions and enabling iterative revision. However, standard broadcast-style MAD makes peer answers visible without requiring agents to engage with a particular peer claim. As a result, reliable reasoning may be suppressed by conflicting or majority responses, limiting achievable performance, while erroneous reasoning may persist and...
-
41
Consider, Then Choose: Order-Invariant Decisions in System One Models
Jianguo Huang, Yao Long Teng, Yanchen Deng, Bo An
cs.AI · cs.CL
System One models answer typed questions in a single forward pass and promise the same answer for the same input. For choice questions, this promise fails: the answer depends on the order of the options, increasingly so as they grow in number, and averaging over their cyclic shifts reduces this dependence without removing it. Scoring each option alone, which the order cannot affect, shows that the order changes the answer mostly when the...
-
42
QORH: Learning Query-Specific Ordered Rule Hypergraphs for Inductive Knowledge Graph Link Prediction
Naixing Xu
cs.AI
Knowledge graph link prediction involving unseen entities and relations requires learning transferable reasoning patterns from observed graph structure. Existing methods based on relation graphs primarily capture pairwise dependencies, limiting their ability to preserve the compositional semantics, relation ordering, and role information of complete path rules. To address this limitation, we propose QORH (Query-specific Ordered Rule...
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.