ICLR 2026PastLarge language modelsML systemsAgents
ICLR 2026 Workshop on Memory for LLM-Based Agentic Systems
ICLR 2026 Workshop MemAgents
- Submission deadline
- Feb 14, 2026, 11:59 UTCOpenReview-synced 2026-02-14 11:59 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (70)
Fetched from OpenReview (v2) on 2026-06-10.
A Lightweight, Domain-Adaptive Memory System for LLM Agents
Adaptive Memory Admission Control For LLM Agents
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Agentic Memory Should Localize Compression
Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction
AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
Belief Engine: Bayesian Memory for Configurable Opinion Dynamics in LLM Agents
CAOTE: Optimizing KV Cache Memory Through Attention Output Error-based Token Eviction
Chow–Liu Ordering for Long-Context Reasoning in Chain-of-Agents
CloneMem: Benchmarking Long-Term Memory for AI Clones
CoMem: Context Management with A Decoupled Long-Context Model
Compute Allocation for Reasoning-Intensive Retrieval Agents
CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems
Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory
DialSim: A Dialogue Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents
Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents
Distilling Feedback into Memory-as-a-Tool
Do LLMs Benefit From Their Own Words?
ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents
Entropic Memory: A Thermodynamics-Inspired Consolidation Mechanism for Lifelong Agent Learning
Episodic Memory from Compression Boundaries in Latent Representation Space
Epistemic Memory Failures in Long-Form Narrative Agents: A Deployment Study
Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
Evaluating Memory Structure in LLM Agents
Experiential Reflective Learning for Self-Improving LLM Agents
FactorMiner: A Self-Evolving Agent with Skills and Experience Memory for Financial Alpha Discovery
Fast-Write, Deep-Read: EcphoryRAG as Dynamic Associative Memory for Lifelong Agents
Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison
From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
GAM: Hierarchical Graph Memory for LLM-based Agents
Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction
INFMEM: Learning System-2 Memory Control for Long-Context Agent
Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
LaCy: What Small Language Models Can and Should Learn into Limited Parametric Memory
Latent Action Reparameterization for Efficient Agent Inference
Learning Multimodal Trajectory Representations for Web Agent Planning
Learning Safe Robot Planning from Unsafe Experiences: An Episodic Memory Approach for LLM-based Agents
Learning to Continually Learn via Meta-learning Agentic Memory Designs
Learning What to Learn: Curriculum Curation for Test-Time Agent Learning
LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents
Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation
Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures
LP-RAG: A Link Prediction-Based Framework for Retrieval-Augmented Generation
MemFly: On-the-Fly Memory Optimization via Information Bottleneck
MemGrad: A Memory-Guided Optimization of Agentic Software Development via Abstracted Textual Gradients
MemoGraph: Augmenting LLMs with Explicit Episodic Memory for Multi-step Mathematical Reasoning
Memory Injection Attacks on LLM Agents via Query-Only Interaction
MEMORY IS RECONSTRUCTED, NOT RETRIEVED: GRAPH MEMORY FOR LLM AGENTS
Memory Transplants for LLM Agents: Disentangling Architecture and Content Transfer under a Code-to-Math Shift
Memory-Efficient Multilingual Embeddings with a Diffusion-LM Backbone
MIRROR: Complementary Encoding and Reconstructive Consolidation for Persistent State in LLM Systems
Multi-Agent Collaborative Framework for Intelligent IT Operations: An AOI System with Context-Aware Compression and Dynamic Task Scheduling
Norm-Guided KV-Cache Eviction for Memory-Efficient Reasoning
PROCED-MEM: BENCHMARKING PROCEDURAL MEMORY RETRIEVAL IN LANGUAGE AGENTS ACROSS DOMAINS
R-KVHash: Reasoning Model KV Cache Compression Via SimHash-based Estimation of Redundant Tokens
Real-Time Procedural Learning From Experience for AI Agents
Retrieval-Augmented LLM Agents: Learning to Learn from Experience
SABER: Small Actions, Big Errors — Safeguarding Mutating Steps in LLM Agents
SelfEvoWM:Self-Evolving Task Discovery and In-Imagination Robot Learning with DROID-Grounded World Models
ShiftBench: Measuring Recovery of Agent Memory Under Distribution Shift
SimpleMem: Efficient Lifelong Memory for LLM Agents
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Spectral Attention Steering for Prompt Highlighting
SuperIntelligent Retrieval Agent: The Next Frontier of Information Retrieval
Tool use is provably more scalable than in-weight memory for Large Language Models
Toward a Theory of Hierarchical Memory for Language Agents
UltRAG: A universal simple scalable recipe for knowledge graph RAG
WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance