# When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents

**Authors:** Runxuan Tang, Haoyu Gao, Yuyan Ding, Junyi Yao, Zihao Zheng, Zecheng Sheng, Liwei Hou  
**Published:** 10 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.14326) · [PDF](https://arxiv.org/pdf/2611.14326) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.14326.html)

## Key numbers

- **5.0%**: while reducing falsification failures to 5.0%
- **1.3%**: while reducing falsification failures to 5.0%, regression damage to 1.3%
- **3.6%**: and harmful committed updates to 3.6%

## Abstract

LLM agents increasingly operate in long-horizon, verifier-rich environments, but current self-improvement mechanisms often write episode-derived lessons directly into memory, making local success an unreliable signal for reusable and safe knowledge. This paper addresses the core question of when an experience-derived behavioral update should be admitted into persistent agent state. We propose Falsification-Gated Self-Evolution (FGSE), a verifier-grounded framework that represents each candidate lesson as a structured hypothesis with an explicit precondition, behavior change, expected effect, and verifier. FGSE applies the hypothesis only in a temporary state, tests it on target-transfer, falsification, and archived-regression probes, and then commits, refines, or rejects it according to measured gain and risk. Across web, app, tool-use, and long-term memory benchmarks, FGSE achieves strong task performance, including 39.8 WebArena success rate, 78.8 AppWorld average completion, and 0.724/0.487 Pass^1 on $τ$-Retail/$τ$-Airline, while reducing falsification failures to 5.0%, regression damage to 1.3%, and harmful committed updates to 3.6%. These results suggest that testing memory updates as hypotheses supports more reliable long-term adaptation.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.