Memory Consolidation for LLM Agents

LLM: Large Language Model

Latest papers

18 papers3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

When Retrieval Is Not Enough: Obsolete Facts in Agent Memory
Oct 26, 2026Oleeviya Babu Poikarayil, Tony Basil Babu, Abdulrahman Nahhas +4Agent Memory Memory Consolidation for LLM Agents
Faculty of Computer Science, Otto-von-Guericke-Universität Magdeburg, Germany · University of Kerala, India · Otto-von-Guericke-Universität Magdeburg, Germany +1
Let Them Sleep: Recursive Self-Pruning Memory for Long-Horizon LLM Agents
Oct 18, 2026Kargi Chauhan, Sadiba Nusrat Nur, Pratibha Revankar +2Memory Consolidation for LLM Agents LLM Agent Memory
University of California, Santa Cruz
Hippo: Training-Free Agent Self-Evolution via Hippocampal Replay
Oct 17, 2026Yutong Song, Jiang Wu, Yuxuan Ren +2Memory Consolidation for LLM Agents LLM Agent Memory
University of California, Irvine · Independent Researcher · Rice University +1
Remember by Asking: Retrieval-Induced Memory Evolution for LLM Agents
Sep 28, 2026Wanqi Zhou, Jiawei Lu, Yang Wang +4LLM Agent Memory Persistent Memory for Language Models
Chang’an University
The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agents
Sep 26, 2026Sasank Annapureddy, Anjaneya Prasad ThamataniMemory Consolidation for LLM Agents LLM Agent Memory
All experiments in this program were designed, executed, and adversarially verified by the PRIMA multi-agent research-and-verification system [1] under the authors’ direction.
Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents
Sep 26, 2026Jinming Hu, Haodong Zhao, Qi Jia +4LLM Agent Memory Agent Memory Management
School of Computer Science, Shanghai Jiao Tong University · School of Computing, National University of Singapore · Shanghai Artificial Intelligence Laboratory
EngramRAG: Dynamic Usage-Weighted Topology and Synaptic Consolidation for Multi-Hop Agentic Memory
Sep 25, 2026Bhavyateja Potineni, Lohit Giri, Anu Jain +2Memory Consolidation for LLM Agents LLM Agent Memory
Independent Researchers
MemoryLACE: Memory Lifecycle-Aware Consolidation and Evidence Retrieval
Sep 2, 2026Meriem Yacoubi, Pia Schmidt, Nenad Petrovic +3Persistent Memory for Language Models Long-Term Conversational Memory
Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich · inovex GmbH · Cerebras Systems Inc.
LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation
Aug 13, 2026Dongfang Li, Zixuan Liu, Junmai Wang +6LLM Agent Memory Persistent Memory for Language Models
Harbin Institute of Technology, Shenzhen
Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory
Jul 20, 2026Qingcan Kang, Mingyang Liu, Shixiong Kai +5LLM Agent Memory Persistent Memory for Language Models
Huawei Noah’s Ark Lab · Department of Computer Science, City University of Hong Kong
Manufactured Confidence: How Memory Consolidation Turns Hearsay into Confident Facts
Jun 28, 2026Alex KwonAI Agent Reliability LLM Agent Memory
Independent Researcher
TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory
Jun 23, 2026Tianyu Yang, Sudipta Paul, Vijay Srinivasan +2LLM Agent Memory Memory Consolidation for LLM Agents
AI Center-Mountain View, Samsung Electronics · University of Notre Dame
Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory
Jun 9, 2026Suozhao Ji, Baodong Wu, Zehao Wang +8Agentic RAG Persistent Memory for Language Models
1Infinigence AI · 2Tsinghua University · 3Shanghai Jiaotong University
SaliMory: Orchestrating Cognitive Memory for Conversational Agents
Jun 2, 2026Kai Zhang, Xinyuan Zhang, Hongda Jiang +11Long-Term Conversational Memory Memorization in Generative Models
Meta Reality Labs
RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents
May 15, 2026Zijie Dai, Shiyuan Deng, Sheng Guan +4Long-Horizon LLM Agents Agent Memory Management
Department of Computer Science and Engineering, The Chinese University of Hong Kong · Huawei Cloud · School of Computer Science, Beijing University of Posts and Telecommunications +2
Useful Memories Become Faulty When Continuously Updated by LLMs
May 13, 2026Dylan Zhang, Yanshan Lin, Zhengkun Wu +4AI Agent Reliability Persistent Memory for Language Models
University of Illinois Urbana-Champaign · IIIS, Tsinghua University
Human-Inspired Memory Architecture for LLM Agents
May 8, 2026Doga Kerestecioglu, Alexei Robsky, Clemens Vasters +2Agent Memory Management LLM Agent Memory
Microsoft
Lightweight LLM Agent Memory with Small Language Models
Apr 9, 2026Jiaquan Zhang, Chaoning Zhang, Shuxu Chen +9Memory Management for LLM Agents Persistent Memory for Language Models
University of Electronic Science and Technology of China · Kyung Hee University · City University of Hong Kong +1

Oct 26, 2026J/K move · Enter open · S save

When Retrieval Is Not Enough: Obsolete Facts in Agent Memory

Oleeviya Babu Poikarayil, Tony Basil Babu, Abdulrahman Nahhas, Het Darshan Mehta+3

Faculty of Computer Science, Otto-von-Guericke-Universität Magdeburg, Germany · University of Kerala, India · Otto-von-Guericke-Universität Magdeburg, Germany+1

Agent Memory Memory Consolidation for LLM Agents Memory Agent Benchmarks Evidence Retrieval

Open paper AskPDF arXiv

Memory-agent benchmarks often collapse retrieval and answer generation into one score, making it hard to tell whether a failure comes from missing an update or from not using an update that was already retrieved. We examine this distinction on the single-hop FactConsolidation task of MemoryAgentBench. With Qwen2.5-7B-Instruct on 6K-history BM25 accuracy drops from 45% to 32% when the retrieved evidence budget grows from 64 to 512 tokens, even though a gold-assisted post-hoc audit finds the newest statement in every retrieved set. Most of the errors occur on questions that also contain an obsolete statement version. Under a frozen prompt and equal four-statement evidence size, replacing one unrelated statement with the obsolete competing statement reduces accuracy from 100% to 44.6% for Qwen2.5 and from 100% to 87.8% for Qwen3-14B, with all 50 harmful paired flips classified as stale. A 32K-history replication likewise favors BM25-64 over BM25-512 (69% versus 58%). These results suggest that retrieving the correct fact is not enough. An obsolete competing statement can be more harmful than an unrelated piece of evidence of the same size.