CORTEXA
← Browse
arxivcs.AIcs.CL2026-06-29

Self-Evolving World Models for LLM Agent Planning

Xuan Zhang, Wenxuan Zhang, See-Kiong Ng, Yang Deng

World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unreliable foresight can be ignored, misused, or even degrade downstream decision-making. In this paper, we introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen. WorldEvolver integrates three modules: (i) Episodic Memory, which exploits real action transitions through retrieval-based simulation; (ii) Semantic Memory, which extracts persistent heuristic rules from prediction-observation mismatches; and (iii) Selective Foresight, which filters low-confidence predictions before integrating them into agent reasoning context. We evaluate WorldEvolver on ALFWorld and ScienceWorld, measuring world model prediction accuracy on Word2World and downstream agent success rate on AgentBoard. Extensive experiments show that WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate, demonstrating that test-time memory revision enhances both predictive fidelity and planning performance.

View free PDFSource page

Related papers

arxivcs.AIcs.CL2026-07-02

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

Jiayin Zhu, Kelong Mao, Yudong Guo, Dengbo He, Sulong Xu, Simiu Gu, et al.

Skills are becoming a reusable operational layer for LLM agents, encoding SOPs, domain rules, tool workflows, scripts, and validation routines. In realistic skill repositories, overlapping skills make reliable skill-use difficult. Final verifier success is too coarse for both eva…

View free PDFSource page
arxivcs.AIcs.CLcs.MA2026-07-08

From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents

Haipeng Ding, Yuexiang Xie, Zhewei Wei, Yaliang Li, Bolin Ding

Tool utilization enables Large Language Model (LLM) agents to interact with the real world and resolve complex tasks. However, existing agent frameworks predominantly rely on static toolsets composed of granular atomic actions (e.g., basic file I/O or single-turn search), which f…

View free PDFSource page
arxivcs.AIcs.CLcs.CR2026-07-08

The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents

Xing Zhang, Yanwei Cui, Guanghui Wang, Ziyuan Li, Wei Qiu, Bing Zhu, et al.

A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures? Skill retirement is the structural constraint that keeps a growing library from drifting below the no-skill baseline, but its guarantee assumes an unbiased…

View free PDFSource page
arxivcs.AIcs.CLcs.MA2026-07-14

Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents

Xing Zhang, Guanghui Wang, Yanwei Cui, Ziyuan Li, Wei Qiu, Bing Zhu, et al.

Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists. In many real applications it does not. We make three claims. First, metrics can be \emph{evolve…

View free PDFSource page
arxivcs.CVcs.AIcs.CLcs.GRcs.MA2026-07-17

Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration

Xiaoye Zhu, Weixin Li, Junan Huo, Bozhong Wang, Jia Zeng, Yi Yang, et al.

A fundamental intent asymmetry plagues modern 3D asset creation: while state-of-the-art 3D toolchains demand precise, executable parameters, ordinary users typically provide vague, underspecified instructions. Current 3D agents treat this ambiguity as noise, defaulting to blind e…

View free PDFSource page
arxivcs.AIcs.CL2026-07-01

Self-Evolving Agents with Anytime-Valid Certificates

Biswa Sengupta

Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produced by the policy being updated. We present \textbf{SEA}, an architecture that confines self-modification to a small steering adap…

View free PDFSource page