When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents

Summary

RSE-Bench is a benchmark for evaluating skill self-evolution in LLM agents under ordinary, non-adversarial noise, covering four domains and six benchmarks. Across three methods and two backbones, noisy learning retains only 25.5% to 42.1% of the aggregate gain of clean self-evolution, depending on noise type. Perturbations confined to execution records and outcome-record pairings cause average losses comparable to input-side noise.