Procedural Memory Under Change: Reuse and Interference in Controlled Web Tasks

2026-09-09 · Yanze Cao arxiv

Procedural memory lets language agents reuse successful routines, but reuse presumes that a stored routine remains applicable. We study what happens when that presumption is deliberately violated. The study combines a retrospective, human-assisted interface-adaptation case from BrowserGym TimeWarp with controlled frozen-memory comparisons on synthetic shopping decisions. During the documented WebShop V1-V6 development path, interface-specific code was adapted while the separately stored high-level procedure was not reported to change; this phase does not constitute an autonomous memory-agent evaluation. In the controlled phase, an early pilot produced one task on which two memory conditions selected a more expensive item while the no-memory condition selected the reference minimum. Follow-up probes did not establish a recurring row-order or identity-binding pattern. We then tested four forms of mismatch: changed quantities, a different evidence representation, a conflict between local and global optimization, and distributed promotion evidence, across 32 formal cells. Each cell used one temperature-0 generation with the same local qwen3:8b configuration and no adaptive retry. Across these pairs, none of the predefined diagnostic interference signatures appeared on the tasks for which they were defined when current-task evidence was explicit and sufficient. The result identifies a tested region of non-interference: a procedural memory can be mismatched without becoming behaviorally disruptive. It does not establish general safety or a mechanism. The remaining question is which additional conditions turn applicability mismatch into observable, memory-caused error.

📄 PDF Abstract BibTeX arXiv:2609.09774

Code (0)

등록된 구현이 없습니다.

What Makes Agent Memory Useful for Reliable Unanswerable Question Handling?

2026-08-28 · Chuanyuan Tan, Junjie Yu, Yuxin Wang, Yining Zheng 외 arxiv

Reliable handling of unanswerable questions (UAQs) is critical for trustworthy LLM-based agents. Although memory is widely used in agent systems, its role in reliable UAQ handling remains unclear. We present a systematic…

Procedural Knowledge at Scale Improves Reasoning

2026-04-01 · Di Wu, Devendra Singh Sachan, Wen-tau Yih, Mingda Chen arxiv

Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat each problem in isolation and do not systematically reuse knowledge from p…

Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents

2026-02-02 · Qirui Mi, Zhijian Ma, Mengyue Yang, Haoxuan Li 외 arxiv

LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. This insufficient experience reuse leads to computational redundancy and in…

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory

2025-12-08 · Sijia Li, Yuchen Huang, Zifan Liu, Zijian Li 외 arxiv

As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories …

Reinforcement Learning

SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills

2026-05-22 · Yingtie Lei, Zhongwei Wan, Jiankun Zhang, Samiul Alam 외 arxiv

Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillE…