What Makes Agent Memory Useful for Reliable Unanswerable Question Handling?

2026-08-28 · Chuanyuan Tan, Junjie Yu, Yuxin Wang, Yining Zheng, Xipeng Qiu, Wenliang Chen 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 study of agent memory for UAQ handling under a unified agentic RAG framework, evaluating four representative memory methods across three UAQ-related datasets and two base models. We find that memory can improve UAQ performance in some settings, but such gains are selective rather than universal and remain fragile under dataset shift. Interestingly, cross-model memory reuse is often more feasible than cross-dataset transfer, suggesting that shifts in answerability patterns pose a greater challenge to memory reuse than changes in the base model itself. We further find that UAQ gains are more strongly preserved through decision guidance than through trajectory shaping, and that memory effectiveness depends strongly on representation. In particular, procedural and rule-based memories often provide the most reliable support for UAQ handling, while memory composition is most effective when procedural guidance is combined with complementary behavioral signals. Overall, our findings suggest that reliable UAQ memory depends less on storing larger amounts of experience and more on preserving transferable behavioral guidance.

📄 PDF Abstract BibTeX arXiv:2608.27924

Code (0)

등록된 구현이 없습니다.

StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance

2026-06-12 · Guanming Liu, Yuqi Ren, Hansu Gu, Peng Zhang 외 arxiv

A central role of personal-agent memory is to turn stored information and prior interactions into future-oriented assistance. In daily use, useful cues come from what the agent observes and how the user interacts with th…

Useful Memories Become Faulty When Continuously Updated by LLMs

2026-05-13 · Dylan Zhang, Yanshan Lin, Zhengkun Wu, Yihang Sun 외 arxiv

Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolidated abstractions distilled across many episodes into reusable, schema-li…

Mem-$π$: Adaptive Memory through Learning When and What to Generate

2026-05-20 · Xiaoqiang Wang, Chao Wang, Hadi Nekoei, Christopher Pal 외 arxiv

We present Mem-$π$, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory stores. Existing memory-augmented agents t…

Reinforcement Learning

Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory

2026-06-08 · Haoran Sun, Wenjie Li, Yujie Zhang, Zekai Lin 외 arxiv

Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering. In such settings, effective agents must reuse prior experience across evolving c…

Question Answering Decision Making

Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents

2026-08-21 · Quang Dao, Purvi Kathalkar, Kenneth Eaton arxiv

Large language model (LLM) agents have demonstrated the ability to solve multi-step tasks requiring planning, tool use, and external information access, yet growing execution histories increase inference cost and expose …