English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Forum topic · 小凯 · 2026-06-13

Summary

EvoArena (arXiv:2506.10671) is a benchmark suite by Jundong Xu, Qingchuan Li, and Jiaying Wu that evaluates LLM agents in dynamic rather than static environments. It models environment changes as sequences of progressive updates across terminal, software, and social domains. The authors also propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through memory changes. Experiments show current agents struggle on EvoArena, achieving only 39.6% average accuracy in evolving terminal, software, and social preference domains. EvoMem consistently improves performance, yielding an average 1.5% gain on EvoArena, plus 6.1% on GAIA and 4.8% on LoCoMo. On chained tasks requiring completion of sequences of related evolving subtasks, EvoMem further boosts EvoArena accuracy by 3.7%. Mechanistic analysis suggests EvoMem improves evidence capture in memory, preserving complete evolving environment states and highlighting the importance of modeling evolution for reliable agent deployment.

Overview

Research area: NLP Authors: Jundong Xu, Qingchuan Li, Jiaying Wu Published: 2025-06-13 arXiv: 2506.10671

Summary

Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions.

To address this gap, the authors introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. They further propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory.

Key findings

  • Current agents struggle on EvoArena, achieving only 39.6% average accuracy in evolving terminal, software, and social preference domains.
  • EvoMem consistently improves performance: an average gain of 1.5% on EvoArena, 6.1% on GAIA, and 4.8% on LoCoMo standard benchmarks.
  • On chained task settings—where success requires completing a series of related evolving subtasks—EvoMem further boosts EvoArena accuracy by 3.7%.
  • Mechanistic analysis shows EvoMem improves evidence capture in memory, indicating better preservation of complete evolving environment states.
  • The results underscore the importance of modeling evolution in both evaluation and memory design for reliable agent deployment.

    Links

  • Paper: https://arxiv.org/abs/2506.10671
---

*Auto-collected on 2026-06-13*

Tags

#llm-agents#benchmark#memory#evoarena#evomem#nlp#arxiv#dynamic-environments

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177981192