cs.AI · 2026-07-07 · No. 46
Artificial Intelligence, 2026-07-07.
30 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
30 entries-
01
LLM-as-a-Verifier: A General-Purpose Verification Framework
Jacky Kwok, Shulu Li, Pranav Atreya, Yuejiang Liu, Yixing Jiang, Chelsea Finn, Marco Pavone, Ion Stoica, Azalia Mirhoseini
cs.AI · cs.CL · cs.LG · cs.MA · cs.RO
Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine the correctness of a solution, as a new scaling axis. To unlock this and demonstrate its effectiveness, we introduce LLM-as-a-Verifier, a general-purpose verification framework that provides fine-grained feedback for agentic tasks without requiring...
-
02
SovereignPA-Bench: Evaluating User-Owned Personal Agents under Evolving Intent, Platform Mediation, and Consent Constraints
Dylan Zongmin Liu
cs.AI
Personal agents are becoming persistent user-owned intermediaries: they remember preferences, filter platform-mediated information, use tools, and negotiate with services. Existing benchmarks evaluate tool use, web navigation, desktop control, personalization, recommendation, and evolving context, but rarely ask whether an agent preserves user sovereignty: advancing the user's current interests while respecting privacy, consent, evidence,...
-
03
Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning
Idan Lev-Yehudi, Vadim Indelman
cs.AI
Planning under uncertainty in continuous domains is essential for autonomous systems, yet computationally demanding. Tree-based search methods such as Monte Carlo Tree Search (MCTS) remain popular, but their branching structure can require sampling budgets that grow exponentially with lookahead depth in the worst case. From a tree perspective, continuous state or action spaces become especially challenging, since the planner must decide where...
-
04
OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement
Adriana Laurindo Monteiro, Nayse Fagundes, Gabriel Mattos Langeloh, Gustavo de Oliveira Kanno, Priscila Louise...
cs.AI · cs.MA
We propose OptiAgent, a multi-agent framework that, given a natural language description of an Operations Research problem, is able to output a solver-ready mathematical formulation as well as executable code. Our architecture prioritizes the mathematical modeling step, where dedicated agents extract structures, such as decision variables and constraints, enabling iterative self-correction. We introduce a novel multi-loop validation...
-
05
Evaluating and Understanding Model Editing for Medical Vision Language Models
Guli Zhu, Chenwei Wu, Liyue Shen
cs.AI
Model editing promises a fast, targeted way to correct post-deployment mistakes in medical vision-language models (VLMs) without costly retraining. However, existing multimodal model editing benchmarks focus on general-purpose tasks and do not reflect realistic clinical domain requirements and variability. To address this, we introduce M3Bench, a clinically grounded benchmark for multimodal model editing that evaluates whether an edit remains...
-
06
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
Zefeng Wang, Minxi Yan, Jinhe Bi, Sikuan Yan, Volker Tresp, Yunpu Ma
cs.AI
Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability. However, a fixed, hand-authored skill is rarely optimal, and cannot adapt to the diversity of tasks an agent encounters. Self-improving agents address this by rewriting their own skill files from execution traces, yielding meaningful gains on challenging benchmarks. Yet...
-
07
MoP-JEPA: Hard-Assigned Predictor Mixtures for Stochastic JEPA World Models
Zhi Song, Ximing Xing, Zhenchao Tang, hanbo Huang, Tianxu Lv, minghao Yang, Zhongzheng Niu, He Bing, Lusheng Wang,...
cs.AI
JEPA world models predict the next latent state with a single deterministic predictor trained by latent regression. We show that this fails structurally when the environment is stochastic: at a branching transition, the regression-optimal predictor outputs the conditional mean of the successor embeddings, a point between the true next states that corresponds to no state at all. We prove this collapse for deterministic and gated...
-
08
EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer
Xingze Gao, Chuanrui Hu, Hongda Chen, Pengfei Yao, Zhao Wang, Yi Bai, Zhengwei Wu, Yunyun Han, Xiaofeng Cong, Jie...
cs.AI
Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for searching, debugging, and verification. Yet current evaluations do not isolate this form of transfer. Agent benchmarks test single-episode task solving; memory benchmarks target information retention rather than procedural reuse. We introduce EvoAgentBench, a benchmark for agent self-evolution...
-
09
Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models
Raj Jaiswal, Dhruv Jain, Rishabh Dhawan, Sree Krishna Uppalapati, Shin'ichi Satoh, Tanuja Ganu, Rajiv Ratn Shah
cs.AI
Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows. Limited domain knowledge, hallucination under multi-step derivation, and distributional sensitivity compound this failure. We propose a step-level reward framework that identifies the first reasoning error, generates targeted structured feedback, and trains the model to revise its solution via policy...
-
10
ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization
Mahnoor Shahid, Hannes Rothe
cs.AI · cs.SC
Compositional generalization, the ability to understand and produce novel combinations of known components, remains a fundamental challenge for modern artificial intelligence. While few benchmarks exist, many focus on linguistic tasks and lack complex, explicit compositional structures. We introduce ClassicLogic, a new benchmark suite designed to evaluate an agent's ability to learn and compose problem-solving strategies. The benchmark...
-
11
Rethinking On-Policy Self-Distillation for Thinking Models
Simran Kaur, Narutatsu Ri, Yinghui He, Liam Fowl, Sanjeev Arora
cs.AI · cs.LG
Self-distillation is a promising recipe for self-improvement in language models. In this setting, a model can serve as its own teacher when given privileged information, such as a solution to a math problem. This seems especially appealing for thinking models, which can use test-time reasoning to absorb the privileged information. Surprisingly, we show that privileged self-distillation degrades thinking models on long reasoning traces: across...
-
12
CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling
Vipul Patel, Anirudh Deodhar, Dagnachew Birru
cs.AI
Workforce scheduling is an NP-hard combinatorial optimization problem requiring simultaneous satisfaction of labor regulations, coverage requirements, employee preferences and operational objectives. Existing CP formulations typically model simplified instances with 6-12 constraints at shift-level granularity and critically lack explicit support for: mandatory break scheduling with midpoint placement control; acuity weighted workload equity;...
-
13
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu,...
cs.AI
Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic evaluations. However, most existing benchmarks evaluate agents in simplified, idealized settings. They typically rely on pre-packaged tool interfaces, overlook critical steps, and assume inputs are clean and fully specified. Consequently, they understate the difficulty...
-
14
The Changing Role of Symbolic Methods in Artificial Intelligence
Jun Sun
cs.AI · cs.LO
Why do intelligent systems need to perform explicit symbolic reasoning? Computer science has traditionally regarded symbolic reasoning as a defining component of intelligence. Yet the remarkable success of modern foundation models raises a fundamental question: if increasingly capable AI systems can operate with little explicit symbolic reasoning, what role do symbolic methods actually play? This article argues that explicit symbolic...
-
15
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Xin Cheng, Xingkai Yu, Chenze Shao, Jiashi Li, Yunfan Xiong, Yi Qian, Jiaqi Zhu, Shirong Ma, Xiaokang Zhang,...
cs.AI · cs.CL
Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose long token sequences in a single forward pass, they suffer from rapid acceptance decay due to a lack of inter-token dependencies. Furthermore, indiscriminately verifying these extended blocks wastes critical batch capacity on tokens with high rejection risks, severely...
-
16
TacReasoner: A Dynamic Tactile-Language Framework for Interactive Reasoning in Real-World Scenarios
Kailin Lyu, Di Wu, Long Xiao, Jianning Zeng, Jianwei He, Chang Lin, Lianyu Hu, Lin Shu, Jie Hao, Ce Hao
cs.AI
Among the five primary human senses, tactile is arguably the most fundamental to survival, as it enables the perception of physical contact and interaction in real-world environments. In this paper, we explore two key challenges of integrating tactile sensing into intelligent systems for multimodal reasoning: (i) insufficient modeling of dynamic tactile signals, which restricts reasoning over temporally evolving properties, and (ii)...
-
17
ASSEMCAD: Production-Ready CAD Assembly Generation from Natural Language
Yurui Dong, Shu Zou, Siqi Li, Nianchen Deng, Hongbin Zhou, Xuemeng Yang, Pinlong Cai, Licheng Wen, Xinyu Cai, Botian Shi
cs.AI · cs.CV
Recent advances in large language models and programmatic CAD have significantly improved Text-to-CAD generation for individual parts. However, production-ready mechanical assembly generation remains largely unsolved. Unlike single-part modeling, assemblies require coordinated reasoning over multiple components, functional interfaces, assembly relations, engineering principles, and physical consistency. Consequently, directly generating...
-
18
Diffusion-Guided Uncertainty-Aware Delayed Policy Optimization
Junqi Tu, Zejiao Liu, Fangfei Li, Yang Tang
cs.AI
Reinforcement learning in real world environments often suffers from severe performance degradation due to delayed feedback. Existing approaches typically mitigate performance degradation caused by observation delays by constructing augmented states or predicting the true states. However, these methods often overlook the inherent discrepancy between delayed state and true states induced by stochastic MDP. We theoretically prove the existence...
-
19
Toward Trustworthy Large Language Model Agents in Healthcare
Hadi Hasan, Safaa Salman, Adam Tai Abou Dargham, Ammar Mohanna, Ali Chehab
cs.AI
Healthcare appointment scheduling remains a persistent operational bottleneck, driven by manual coordination, fragmented legacy systems, and high administrative overhead. These inefficiencies constrain provider availability and degrade patient access to care. This paper presents CareConnect, a safety-first conversational agent for healthcare logistics automation that leverages large language model (LLM) function calling, retrieval-augmented...
-
20
Quantum-Inspired Harmonic Decision Models: A Computational Framework for Music Generation
Josef Pavlíček, Petra Pavlíčková, Martin Molhanec
cs.AI · cs.SD
This paper introduces a quantum-inspired computational framework for harmonic decision-making in music. The proposed approach formulates harmonization as an optimization problem within a structured combinatorial space, where multiple candidate chord sequences are evaluated under interacting musical constraints. The model combines an interference-based harmonization stage with a classical optimization procedure grounded in tonal harmony. The...
-
21
STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training
Qiuyi Qi, Tian Liang, Mutian Bao, Jinjian Zhang, Dongnan Liu, Wei Zhou, Linjian Mo, Ming Kong, Jie Liu, Feng Zhang, Qiang Zhu
cs.AI
Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on long-horizon tasks. However, sparse and delayed rewards often lead to trajectory neglect, in which agents lose focus on the task goal and interaction history at intermediate steps. Prior work has explored step-level supervision using Shannon-entropy-based uncertainty signals, which conflate inherent state complexity with agent confidence and...
-
22
Medi-Gemma: A Hybrid Clinical Decision Support System Integrating Deterministic EMR Analytics and Retrieval-Augmented Generation
Mohammed Saim Ahmed Quadri, Yunzhe Xue, Justin W. Ady, Usman Roshan
cs.AI
Deploying Large Language Models (LLMs) in high-stakes clinical settings remains limited by structural hallucinations, weak deterministic reasoning over tabular patient data, and omissions in vector retrieval. This paper presents the architecture and validation of Medi-Gemma, a Clinical Decision Support System (CDSS) for wound pathology triage and workflow automation. The platform introduces a decoupled framework that separates clinical...
-
23
CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs
Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo,...
cs.AI
Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their reliability in real-world applications. This deficiency arises from a lack of systematic mechanisms to incorporate constraint information during the generation process. While existing approaches attempt to mitigate this by relying on external tools or task...
-
24
AgenticPD: A Stage-Aware Agentic Framework for Physical Design QoR Optimization
Shuo Ren, Zijin Cheng, Yaohui Han, Libo Shen, Leilei Jin, Wanting Tian, Rongliang Fu, Chao Wang, Bei Yu, Tsung-Yi Ho
cs.AI
Physical design quality-of-results~(QoR) optimization is hard and expensive. Choices made at one stage can help or hurt later stages. Each evaluation requires a costly EDA run through the full flow. While existing methods still treat optimization as flat parameter tuning or a LLM-based script generation task, we present AgenticPD, a stage-aware agentic framework for physical design QoR optimization. Instead of re-running the full flow after...
-
25
FM-ChangeNet: Learning Change through Pathwise Feature Transport
Roie Kazoom, George Leifman, Genady Beryozkin
cs.AI · cs.CV
We present FM-ChangeNet, a pathwise-supervised framework for change detection that reformulates bi-temporal reasoning as continuous transport in feature space rather than static endpoint comparison. Given encoded pre and post-temporal representations, we construct intermediate latent states and learn a time-conditioned velocity field $\hat{v}_θ(z_t,t)$ along the transformation trajectory. This pathwise formulation constrains the predictor...
-
26
FORGE: Research-Trajectory Hijacking Attacks on Deep Research Agents
Yue Pan, Ziheng Zhang, Junxiang Lei, Changhao Jia, Qingyi Si, Hongcheng Guo
cs.AI
Deep research agents decompose open-ended queries into subtasks, retrieve web evidence over multiple rounds, and synthesize long-form reports. This workflow creates a planning-layer poisoning surface: adversarial documents that enter the retrieval pool can steer follow-up questions and turn a local injection into report-level contamination. We present FORGE (Fabricated Orchestrated Reasoning chain for aGent Exploitation), a two-level attack...
-
27
Integrated Altruistic and Fairness Preference Induces Advanced Mutual Cooperation in Sequential Social Dilemmas
Yu Wei, Yukiko Ogura, Yoshiyuki Ohmura, Ildefons Magrans de Abril, Hoshinori Kanazawa, Yasuo Kuniyoshi
cs.AI
Inducing cooperation among distributed agents is still a difficult problem in the field of multi-agent reinforcement learning (MARL), particularly in social dilemma situations. There, individual interests are misaligned with the common good and individual rationality leads to suboptimal group outcomes. In contrast, humans are able to achieve cooperation with one another in such situations. A common explanation for such cooperative behavior is...
-
28
Formal Disco: Scalable Open-Ended Generation of Formally Verified Programs
Gabriel Poesia, Simon Henniger, Tzu-Han Hsu, Yilun Du, Nada Amin
cs.AI
The cost of producing code is rapidly diminishing with increasingly capable AI agents, while quality assurance of generated programs has not kept pace. Formal verification provides the strongest possible guarantees, but the ability of AI models to work with verification-aware languages is hindered by the scarcity of human-written examples of programs in those languages. To tackle this prevalent data scarcity issue, we propose Formal Disco: a...
-
29
MRMS: A Multi-Resolution Memory Substrate for Long-Lived AI Agents
Jizhizi Li, Amy Shi-Nash
cs.AI
Long-lived AI agents require continuity across interactions, but continuity cannot be obtained by simply extending the prompt window. An agent must preserve useful prior experience, retrieve it selectively, distinguish personal context from external evidence, and revise memory when the underlying situation changes. We propose an architectural memory substrate organized along two orthogonal axes: a representational axis spanning structured...
-
30
Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority
Xue Qin, Simin Luan, Cong Yang, Zhijun Li
cs.AI · cs.CR
Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed. This reopens a question that alignment techniques answer only probabilistically: after an agent has adapted in the field, is the running system still confined to what its operator authorised? Here we show that confinement can be guaranteed as an invariant of the agent's execution...
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.