Memory-Augmented Language Model Agents

Follow this topic Ask about this topic

Momentum

50 papers in the last four weeks, up 233% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 275

All topics

Selective Memory Retention for Long-Horizon LLM Agents
Jun 28, 2026Pranath ReddyLLM Agent Memory Persistent Memory for Language Models
Independent Researcher, Huntsville, Alabama, USA.
Memory as an Attack Surface in LLM Agents: A Study on Multiple-Choice Question Answering
Jun 27, 2026Shahnewaz Karim Sakib, Anindya Bijoy DasAgent Memory Poisoning LLM Agent Reliability
University of Tennessee at Chattanooga, TN 37403, USA · The University of Akron, OH 44325, USA
When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration
Jun 27, 2026Luís Brito, Carlos BaqueroLLM Agent Security Multi-LLM Collaboration
Escola Superior de Tecnologia e Gestão (ESTG), Politécnico de Viana do Castelo (IPVC), Portugal · Faculdade de Engenharia (FEUP), Universidade do Porto (UP), Portugal
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
Jun 25, 2026Shicheng Ye, Chao YuContinual Learning for LLM Agents LLM Agent Training
Sun Yat-sen University
Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents
Jun 24, 2026Xushuo Tang, Junhe Zhang, Zihan Yang +4Conversational Agents Text Generation
UNSW Sydney · Chang’an University · RAIDS Lab +2
Bridging the Post-discharge Gap: A Traceable Multi-agent Framework for Safe and Continuous Care
Jun 24, 2026Runwei Guan, Yi Zhou, Heyi Lin +12Retrieval-Augmented Generation Multi-Agent LLM Systems
Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 511453, Guangdong, China. · Distinct Healthcare, Shenzhen, 10587, Guangdong, China.
SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation
Jun 23, 2026Chenyang Zhu, Jiayu Yao, Kushal Chawla +10Agent Failure Analysis Long-Horizon Agent Evaluation
1AI Foundations, Capital One · 2General Intelligence Com · Department of Engineering Sciences and Ap
ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling
Jun 23, 2026Heng Ping, Arijit Bhattacharjee, Peiyu Zhang +5Multi-Agent System Optimization LLM Agent Memory
University of Southern California · Iowa State University · Cisco AI Research
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
Jun 23, 2026Shiding Zhu, Yudi Qi, Yajie Wang +6LLM Agents Self-Evolving Agents
Zhejiang University · Shenzhen International Graduate School, Tsinghua University · Independent Researcher +3
Self-Compacting Language Model Agents
Jun 22, 2026Tianjian Li, Jingyu Zhang, William Jurayj +5Efficient Language Model Inference Metacognition in Language Models
♠Johns Hopkins University · ♡Apple
Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation
Jun 22, 2026Julia Belikova, Rauf Parchiev, Evgeny Egorov +4LLM Agent Memory LLM Agent Evaluation
AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts
Jun 18, 2026Yanyu Yao, Shangze Li, Zhi Zheng +4Persistent Memory for Language Models Long-Term Conversational Memory
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China · Anhui University, Hefei, China
FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness
Jun 16, 2026Pianran Guo, Pengcheng Zhou, Yucheng Jian +3Multimodal Reasoning LLM Agents
Beijing University of Posts and Telecommunications · Wuhan Eonray Technology Co., Ltd. · Queen Mary University of London
VisualClaw: A Real-Time, Personalized Agent for the Physical World
Jun 15, 2026Haoqin Tu, Jianwen Chen, Zijun Wang +14Continual Learning for LLM Agents AI Agent Benchmarks
1UC Santa Cruz · 2UNC-Chapel Hill · 3Google +1
FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion
Jun 14, 2026Zixin Rao, Wentian Zhu, Chan Aristella Lu +5Adversarial Attacks on LLMs LLM Agent Security
University of Georgia · University of Chicago · University of Illinois Urbana-Champaign
Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents
Jun 12, 2026Sina Hajimiri, Masih Aminbeidokhti, Jose Dolz +4Web Agent Benchmarks LLM Agent Evaluation
ServiceNow AI Research · ÉTS Montreal · University of British Columbia +1
Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation
Jun 12, 2026Faramarz JabbarvaziriLarge Language Model-Guided Optimization LLM Agent Workflow Optimization
AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition
Jun 12, 2026Jixuan Chen, Jianzhi Shen, Haoqiang Kang +10LLM Agent Orchestration Embodied AI
University of California, San Diego · 2Johns Hopkins University · University of Washington +1
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
Jun 12, 2026Yongheng Zhang, Ziang Liu, Jiaxuan Zhu +17LLM Tool Use Long-Horizon LLM Agents
Tencent Youtu Lab · Tsinghua University · Sun Yat-sen University +2
Poker Arena: Multi-Axis Profiling of Strategic Reasoning and Memory in LLMs
Jun 11, 2026Pratham Singla, Shivank Garg, Vihan SinghGame-Playing Agents Strategic Reasoning Risks in Language Models
Indian Institute of Technology Roorkee · Raeth AI
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Jun 11, 2026Jundong Xu, Qingchuan Li, Jiaying Wu +11Benchmark Design Long-Horizon Agent Evaluation
National University of Singapore · Singapore Management University · University of Washington +5
Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents
Jun 10, 2026Hao-Lun Hsu, Nikki Lijing Kuang, Boyi Liu +2Hierarchical Memory Long-Horizon Agent Tasks
Duke University · Snowflake AI Research
ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning
Jun 9, 2026Yunhan Jiang, Wenbin Duan, Shasha Guo +3Long-Horizon LLM Agents Agent Memory Management
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences
CoCoSI: Collaborative Cognitive Map Construction for Spatial Intelligence
Jun 9, 2026Yiming Zhang, Ruoxuan Cao, Zhihang ZhongMultimodal Large Language Models Multi-Agent LLMs
2Cornell University · 1Shanghai Jiao Tong University
Civil Court Simulation with Large Language Models
Jun 8, 2026Yifan Chen, Haitao Li, Kaiyuan Zhang +3Multi-Agent LLMs Legal Reasoning
Beijing University of Posts and Telecommunications, Beijing, China · Tsinghua University, Beijing, China
Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care
Jun 8, 2026Aiyuan Yang, Canbin Piao, Chengfeng Dou +25RL for Language Models Healthcare
Baichuan AI and THUBPM Group, Tsinghua University
ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems
Jun 7, 2026Zhixun Tan, Qiang Chen, Tairan Huang +2Multi-Agent LLM Systems Multi-Agent Coordination
Central South University · The Hong Kong University of Science and Technology
MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback
Jun 6, 2026Suleyman Armagan Er, Danilo Ribeiro, Yogesh Virkar +5Tool-Using Agents LLM Tool Use
AWS AI · University of Washington
Rosetta Memory: Adaptive Memory for Cross-LLM Agents
Jun 5, 2026Hao Yang, Shiqi Shen, Haoxuan Li +3LLM Agent Memory Persistent Memory for Language Models
Gaoling School of Artificial Intelligence, Renmin University of China · Weixin, Tencent · Institute for Artificial Intelligence, Peking University
AdMem: Advanced Memory for Task-solving Agents
Jun 5, 2026Runzhe Wang, Huilin Lu, Shengjie Liu +2Continual Learning for LLM Agents LLM Agent Memory
Princeton University · Amazon · Arm

Jun 28, 2026, cs.AIJ/K move · Enter open · S save

Selective Memory Retention for Long-Horizon LLM Agents

Pranath Reddy

Independent Researcher, Huntsville, Alabama, USA.

LLM Agent Memory Persistent Memory for Language Models Long-Horizon LLM Agents Agent Memory Management Memory-Augmented Language Model Agents

Open paper AskPDF arXiv

When does retention matter for memory-augmented LLM agents? We study this with TraceRetain, a lightweight framework for bounded external memory in frozen LLM agents that scores entries by interpretable features (success, age, access frequency, redundancy, specificity, similarity, downstream utility) and evicts the lowest-scoring ones at capacity. On clean ALFWorld with gpt-5-mini, external memory robustly improves over no memory across two seeds, but differences among bounded retention policies fall within Wilson 95% CIs: clean ALFWorld at T=100 to T=200 does not naturally exhibit the memory pollution retention is designed to address. Under a controlled noisy-write stress (75% synthetic distractors), unbounded memory and FIFO-K50 degrade on Precision@5 (20.2% to 12.4% and 15.8% to 3.8%) while TraceRetain-CEM is essentially unchanged (16.9% to 16.6%) and preserves 97/100 task success. The mechanism: unbounded memory has the highest mean similarity (0.87) but lowest precision, indicating failed distractors close to the query in embedding space. Held-out in-distribution evaluation shows memory-augmented policies solving 47 to 49 of 50 tasks vs. 39/50 for no memory. Bounded retention buys memory and step efficiency on saturated clean benchmarks at no task-success cost, and only differentiates from cache heuristics when streams contain noise.

Momentum

Related topics

Latest papers 275