paper-with-me

Papers

EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer

2026-07-06 · Xingze Gao, Chuanrui Hu, Hongda Chen, Pengfei Yao, Zhao Wang, Yi Bai, Zhengwei Wu, Yunyun Han, Xiaofeng Cong, Jie Gui, Yafeng Deng, Teng Li arxiv

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 via Ability-guided transfer across four agentic domains: web research, algorithmic reasoning, software engineering, and knowledge work. EvoAgentBench extracts trace-grounded Abilities from agent executions, canonicalizes them into operational units, and builds domain-specific Ability Graphs linking tasks that share procedural overlap. By design, every test task is backed by verified training-side Ability support. Across a 528/267 train/test split, two scaffolds, and three backbones, curated Ability content transfers reliably across model families, but no current automatic method sustains positive gain in all settings. EvoAgentBench shifts self-evolution evaluation from aggregate accuracy comparison to fine-grained diagnosis of experience encoding, routing, and uptake. The benchmark is publicly available at https://huggingface.co/datasets/EverMind-AI/EvoAgentBench.

📄 PDF Abstract BibTeX arXiv:2607.05202

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization

2026-02-04 · Jiarui Yuan, Tailin Jin, Weize Chen, Zeyuan Liu arxiv

True self-evolution requires agents to act as lifelong learners that internalize novel experiences to solve future problems. However, rigorously measuring this foundational capability is hindered by two obstacles: the en…

Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization

2026-04-25 · Ziyang Liu, Xinyan Guo, Xuchen Wei, Han Hao 외 arxiv

While recent autonomous agents demonstrate impressive capabilities, they predominantly rely on manually scripted workflows and handcrafted heuristics, inherently limiting their potential for open-ended improvement. To ad…

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation

2026-05-10 · Ye Yu, Xiaopeng Yuan, Haibo Jin, Heming Liu 외 arxiv

Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution i…

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

2026-07-31 · Dong Yan, Jian Liang, Dapeng Hu, Ran He 외 hf

Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-e…

Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

2025-11-25 · Tianxin Wei, Noveen Sachdeva, Benjamin Coleman, Zhankui He 외 arxiv

Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and evolution remain largely underexplored. Ex…