paper-with-me

홈 › Papers

Tree-of-Experience: Hierarchical Experience Management for Self-Evolving Agents

2026-08-10 · Zihao Deng, Yining Zhu, Leiming Wang, Junbo Wang, Jingfei Lu arxiv

Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically refine individual trajectories or abstract shared knowledge from related trajectories, but their experience representations are often disconnected from the underlying reasoning process. This limits feedback attribution, cross-task transfer, and update and retrieval efficiency, particularly in complex reasoning tasks with outcome-level feedback. To overcome this limitation, we propose \textbf{T}ree-\textbf{o}f-\textbf{E}xperience (ToE), a structured experience-management framework that aligns experience organization with the hierarchical reasoning process of LLM agents. Specifically, ToE organizes the experience into a shared tree of analytical perspectives and reasoning paths, whose reliability is calibrated through environmental outcomes to support systematic updating, transfer, and efficient retrieval. The experimental results on \textsc{Game of 24} and \textsc{FinEvolveBench} show that ToE substantially improves both problem-solving performance and efficiency. On \textsc{Game of 24}, ToE achieves a 31.4\% relative improvement in accuracy over the experience-free ToT baseline. On \textsc{FinEvolveBench}, ToE improves tsIC by an average of 41.24\% over the experience-free pipeline across 12 evaluation settings, whereas conventional experience-management methods often underperform experience-free baselines.

📄 PDF Abstract BibTeX arXiv:2608.09044

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Tree-of-Experience: A Structured Experience-Management Solution for Self-Evolving Agents under Low-Repetition and Implicit-Reward Environments

2026-06-05 · Zihao Deng, Yining Zhu, Leiming Wang, Jingfei Lu 외 arxiv

Experience-based self-evolution is crucial for LLM agents, but existing benchmarks often assume explicit goals, stable task patterns, and clear feedback. We study a more challenging setting: low-repetition tasks with imp…

Manipulating the Distributions of Experience used for Self-Play Learning in Expert Iteration

2020-05-30 · Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Cameron Browne

Expert Iteration (ExIt) is an effective framework for learning game-playing policies from self-play. ExIt involves training a policy to mimic the search behaviour of a tree search algorithm - such as Monte-Carlo tree sea…

Board Games

StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management

2026-01-09 · Ruizhe Zhang, Xinke Jiang, Zhibang Yang, Zhixin Zhang 외 arxiv

Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstab…

Reinforcement Learning

DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees

2026-06-02 · Haoran Tan, Zeyu Zhang, Zhicheng Cao, Rui Li 외 arxiv

Large Language Model (LLM)-based agents increasingly rely on memory to learn from experiences over continual interactions. However, storing experiences as independent, flat units leads to substantial redundancy and retri…

ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models

2026-05-09 · Yanbin Hu, Jin Cui, Jiayi Lu, Ruixuan Yang 외 arxiv

Memory capacity is a critical factor determining the performance of Vision-Language-Action (VLA) models in long-horizon manipulation tasks. Existing memory-augmented architectures primarily rely on linear or flat storage…