NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
304 results for “keyword:"agent memory"” in ICLR 2027. 70 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]OWG: Structuring Agent Evidence as Outcome-Witness Graphs for Efficient Long-Horizon Task Closure▼4.3k2.00
[PDF]Recursively Updated Summaries Can Amplify a Remembered Betrayal’s Effect on a Qwen3-8B Agent’s Stated Willingness▼4.3k2.00
[PDF]Rewriting Is Forgetting: Zero Rewrite Capture and Budgeted Reading for Long Horizon Agent Memory▼1361.33
[PDF]SLICE-Mem: Salience-Gated Lightweight Information Curation for Efficient LLM Agent Memory▼4.3k2.00
[PDF]Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents▼4.5k2.67
[PDF]Evidence Is Not Authority: A Causal Study of State Arbitration in Long-Horizon Agent Memory▼1.2k1.67
[PDF]Experience Is Not Knowledge: Where the Decision Knowledge in an Agent's Memory Comes From▼1361.33
[PDF]From Hesitation to Intuition: Internalizing Test-Time Adaptation into LLM Agents via On-Policy Self-Distillation▲3972.67
[PDF]When Agents Should Not Remember: Habitual Execution for Retrieval-Efficient Long-Running LLM Agents▼1361.33
[PDF]Enabling Timely Guidance before Skill Retrieval: Retaining Helpful Warm Tips in Agent Context▲3972.67
[PDF]One Tree, Three Roles: Goal-Structured Extraction, Admission, and Reuse of Procedural Memory▲3972.67
[PDF]When Evidence Changes: Evaluating Memory Repair and Re-reading in Language-Model Agents▼4.3k2.00
[PDF]SM2-AHD: Search Experience Memory and Meta-Cognitive Reflection for LLM-Based Automatic Heuristic Design▼1361.33
Withdrawn or desk rejected (70)
[PDF]Read First, Look on Doubt: A Text-First Framework for Long-Video Question AnsweringWithdrawn2.00
[PDF]When Stale Constraints Go Unchecked: A Budgeted Verification Failure and the Limits of a Simple RuleWithdrawn1.33