EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
- Published
- Source
- arXiv
- Paper number
- 410
- Field
- LLMs / NLP
- arXiv ID
- 2606.13681
Key points
- EvoArena is a dynamic agent benchmark in which terminal, software, and social environments evolve across versions.
- Even the current strongest agents achieve only 39.6 percent on average, which shows that adapting to dynamic environments is still a major challenge.
- EvoMem is a git-like memory that stores memory changes as patch history, including pre-state, post-state, the reason for the change, and the evidence.
- EvoArena delivers consistent performance gains of +1.5 percent, chain-level +3.7 percent, GAIA +6.1 percent, and LoCoMo +4.8 percent.
- In software regression analysis, the PASS_TO_PASS failure rate drops from 9.09 percent to 6.32 percent on average.
- The biggest improvement, +5.2 percent, appears in time-trajectory and multi-pattern synthesis questions, which confirms the value of evidence preservation.
Paper links
External research summaries. These are not HDATF publications or measured product results.