arXiv AI October 9, 2026 By Guanghao Wu, Zhuo Cai, Shoujin Wang

MemTrial: Learning When to Trust Memory in LLM Portfolio Agents

MemTrial is a portfolio‑management agent that learns when to trust its memory of past experiences. It evaluates each experience by drafting decisions with and without that experience, using a fractional factorial design to compute a Banzhaf‑value credit that isolates the experience’s true impact. By pooling noisy credits across dates with a hierarchical Bayesian model and only acting when predictions are reliable, MemTrial outperforms other experience‑learning agents and remains conservative when uncertain, achieving up to 21.2% higher utility and outperforming all LLM baselines on InvestorBench.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Oct 15

MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs

arXiv:2605.08374v4 Announce Type: replace Abstract: Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retr...

By Junwei Liao, Haoting Shi, Ruiwen Zhou, Jiaqian Wang, Shengtao Zhang, Wei Zhang, Ying Wen, Zhiyu Li, Feiyu Xiong, Bo Tang, Weinan Zhang, Muning Wen

llms agents reinforcement-learning benchmarks

arXiv Machine Learning

Sep 22

MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents

arXiv:2609.24259v1 Announce Type: new Abstract: The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over...

By Ruike Cao, Fanyu Zhao, Fugen Yao, Liang Dong, Jian Xu, Guanjun Jiang, Yifei Zhao, Han Zhang, Li Xiao

llms agents reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Jun 30

MemDelta: Controlled Baselines and Hidden Confounds in Agent Memory Evaluation

arXiv:2606. 29914v1 Announce Type: cross Abstract: Agent memory systems are increasingly evaluated against RAG and full-context baselines, but reported gains often mix changes in the memory method with changes in the language model, embedding model, or retrieval pipeline, making it unclear what is actually being measured.

By Kuan Wang

llms rag agents

arXiv Computation and Language

Oct 22

MemoryTax: The Bitter Lesson of Agent Memory

arXiv:2610.29823v1 Announce Type: new Abstract: Agent memory systems such as Mem0 and Zep decide what to keep before any question arrives; coding agents keep the raw history and let the model search...

By Zedong Peng

llms agents

arXiv AI

Oct 7

Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory

The paper investigates how large language model agents can over-rely on agentic memory, a phenomenon where retrieved memories distort inference even when they are correctly stored and retrieved. It shows that memory is helpful when past experience fully transfers to the current task but becomes misleading under partial query-memory overlap, a pattern confirmed by controlled experiments. To address this, the authors propose MEMTRIM, a plug‑and‑play framework that indexes memory evidence at write time and limits its reuse at read time, thereby reducing over-reliance without retraining and preserving useful memory benefits across models and memory architectures.

By Luoxi Tang, Yuqiao Meng, Nilesh Auradkar, Muchao Ye, Dazheng Zhang, Zhaohan Xi

llms rag agents benchmarks

arXiv AI

Aug 25

CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories

arXiv:2608.22533v1 Announce Type: new Abstract: Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and v...

By Zheyuan Deng, Binghang Lu, Hanqi Feng, Shirley Huang, Dianzhuo Wang, Yuanda Xu, Zhiwei Zhang, Yige Sun, Changhong Mou, Runyu Zhang, Yuexing Hao, Barnabas Poczos, Xiaomin Li

llms agents

One email a morning, machine-written

Related stories

MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs

MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents

MemDelta: Controlled Baselines and Hidden Confounds in Agent Memory Evaluation

MemoryTax: The Bitter Lesson of Agent Memory

Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory

CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories