paper-with-me

Papers

ProPlay: Procedural World Models for Self-Evolving LLM Agents

2026-06-11 · Yijun Ma, Zehong Wang, Yiyang Li, Ziming Li, Xiaoguang Guo, Weixiang Sun, Chuxu Zhang, Yanfang Ye arxiv

Self-evolving agents are expected to improve through interaction without external supervision, but this remains difficult in partially observable environments where agents must explore actively, learn from limited feedback, and decide when to trust prior experience. Existing LLM-agent methods often rely on memory or planning modules, yet they rarely close the loop between them to continually refine an internal understanding of environment dynamics. We introduce ProPlay, a procedural world model that supports procedure-level preplay, where agents can rehearse future procedural paths using the learned world knowledge. Rather than representing experience as isolated rules or low-level action constraints, ProPlay abstracts successful trajectories into procedures and organizes them in a procedure graph that captures causal transitions among task stages. Each transition is associated with a reliability record embedding to estimate its task-specific contribution from past outcomes. Before each episode, ProPlay simulates future procedural trajectories over known graph structures as structured soft guidance; after execution, it refines the graph using environment feedback. Experiments on public benchmarks show that ProPlay consistently improves environment understanding and self-evolution capability over strong baselines. Our code has been released in https://github.com/antman9914/proplay.

📄 PDF Abstract BibTeX arXiv:2606.12780

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

2026-09-08 · Yuxing Lu, Yicheng Chen, Shanchan Wu, Sercan Ö. Arık hf

Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions through unconstrained generation over an accumulating history, leaving imp…

Procedural Generalization by Planning with Self-Supervised World Models

2021-11-02 · ICLR 2022 4 · Ankesh Anand, Jacob Walker, Yazhe Li, Eszter Vértes 외

One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks. However, the generalization ability of …

BenchmarkingMeta-LearningModel-based Reinforcement LearningRepresentation Learning

WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents

2026-01-13 · Yuqing Zhou, Zhuoer Wang, Jie Yuan, Hong Wang 외 arxiv

Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks, tend to repeat the same failure patterns, and show substantial run-to-run variability. Fixing failu…

HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research

2025-08-04 · Yinghao Zhu, Yifan Qi, Zixiang Wang, Lei Gu 외 arxiv

The rapid proliferation of scientific knowledge presents a grand challenge: transforming this vast repository of information into an active engine for discovery, especially in high-stakes domains like healthcare. Current…

ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis

2025-08-06 · Huiya Zhao, Yinghao Zhu, Zixiang Wang, Yasha Wang 외 arxiv

The efficacy of AI agents in healthcare research is hindered by their reliance on static, predefined strategies. This creates a critical limitation: agents can become better tool-users but cannot learn to become better s…

Medical Diagnosis