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
134 results for “keyword:"long term memory"” in ICLR 2027. 30 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learning When Evidence-Sensitive Guidance Helps: Calibrating Counterfactual On-Policy Distillation for Memory-Grounded Question Answering▼4.3k2.00
[PDF]Not All Memory Updates Are Equal: A Benchmark for Typed Revision in Long-Term LLM Agents▼4.3k2.00
[PDF]LifeMemBench: Benchmarking Long-Term Memory for Evolving User States through Personalized Planning▼4.3k2.00
[PDF]Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents▼4.5k2.67
[PDF]SIRRA: Matched Evaluation of Standing-Instruction Reapplication after Temporary Non-Applicability▼4.3k2.00
[PDF]What Did the Agent See? Implanting False Memories in Multimodal AI Agents through Black-Box Visual Attacks▲3972.67
[PDF]Beyond Query-Memory Matching: Path-Aware Anchor-Guided Retrieval for Long-Term Agent Memory▼1.2k1.67
[PDF]STRATA: Spatiotemporal Alignment of Agentic Memory for Long-Horizon Preference Tracking▼1611.50
[PDF]Generation–Evaluation Coupling in LoCoMo: A Construct-Validity Audit of Long-Term Memory Evaluation▼1.2k1.67
[PDF]SafeDrift: Reliability-Audited Longitudinal Safety Evaluation of Memory-Augmented Mental-Health Agents▲6.1k2.00
[PDF]AffectLedger: Preserving Affective Evidence and Reconstructing Longitudinal Context for LLM Agents▼5.8k2.33
[PDF]Answer Error Forgetting: Disentangling Memory from Temporal Reasoning over Continual Knowledge Streams▼4.3k2.00
[PDF]NCCA: Nested Credit with Conditional Amplification for LLM-Based Conversational Recommendation▼4.3k2.00
[PDF]GeMS-SC: Learning a Cross-Attentive State-Skill Policy for Runtime Graph-Memory Control in Long-Horizon Agents▲5103.00
[PDF]TaskFid: Benchmarking Agent Memory for Evolving Task-State Fidelity Across Threads and Sessions▼4.3k2.00
[PDF]From Memory Access to Evidence Satisfaction: Diagnosing and Resolving Demand–Evidence Misalignment▼5.8k2.33
Withdrawn or desk rejected (30)
[PDF]H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via A Hybrid StructureWithdrawn2.40
[PDF]ContextGraph: Improving Coding Agents with Agent-Selected Lessons from ExperienceDesk rejected2.67
[PDF]From Recurrence to Consequence: Risk-Aware One-Shot Memory Consolidation for Long-Term LLM AgentsWithdrawn2.00