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
201 results for “keyword:"long term"” in ICLR 2027. 33 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics▼4.5k2.25
[PDF]Can Agents Develop Private Shorthand with You? Benchmarking Dyadic Convention Formation in Long-Term Conversations▲5.4k3.00
[PDF]From Memory to Action: Benchmarking Long-Term Agent Memory in Personal Assistant Environments▼5.8k2.33
[PDF]Revisiting Recurrent Models for Long-Term Time Series Forecasting through Representation Accessibility▼5.8k2.33
[PDF]DuCoMem: Efficient Long-Term Memory for LLMs through Dual Compression and Local Recovery▲5103.00
[PDF]Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations▲3.0k2.33
[PDF]Forecast Privately, Correct Minimally:Bounded Relational Interventions for Multivariate Time Series▼4.3k2.00
[PDF]Not Only Remember, But Also Forget: A Multi‑Scenario Benchmark for Selective Forgetting in Personalized Agents▲3.0k2.33
[PDF]Melo: A Cognitive Science–Inspired Closed-Loop Long-Term Memory Framework for AI Agents▼1.2k1.67
[PDF]Task-Oriented Memory Compilation: Executable State Representations for Long-Context Language Models▼5.8k2.33
[PDF]Conservation Buys Stability and Factoring Buys Counterfactuals in Physical World Models▼4.3k2.00
[PDF]TRACE: Relaying Structural State Beyond the Fixed Input Window for Non-stationary Time Series Forecasting▼4.3k2.00
[PDF]CTIA-ODE: Continuous-Time Inter-Variable Attention for Long-Term Time Series Forecasting▲6.6k3.33
[PDF]Mem-Sonar: Self-Organizing and Self-Navigating Memory via Alternating Reinforcement Learning▼4.5k2.67
[PDF]Retrospective Affective Belief Revision: When New Evidence Changes How LLM Agents Interpret Past Emotions▲11k2.00
[PDF]SQCAD: Lifecycle-Aware Authorization for Scope-Qualified Persistent Memory in Long-Term Agents▼3.7k2.25
[PDF]CERES: RECONCILING DURABLE EVIDENCE AND EVOLVING ACTIVE STATE FOR LONG-LIVED LLM AGENTS▼1.2k1.67
[PDF]UnfoldMem: Unfolding Multimodal Conversational Memory via Iterative Multi-Agent Interaction▼1.2k1.67
[PDF]CorMem: A Brain-Inspired Bipartite Cognitive Map Inducing Latent Relations for Accurate Long-Term Memory Retrieval in LLM Agents▼5.8k2.33
[PDF]Towards Personalized Visual Imagination from Everyday User–MLLM Interaction with Unified Multimodal Models▼4.5k2.67
[PDF]Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants▼5.8k2.33
[PDF]Intrinsic Representation Memory: Decoupling Structural Topology and Semantics for Lifelong Agents▲3.0k2.33
Withdrawn or desk rejected (33)
[PDF]VCRM: Empowering Efficient Memory for Vision-Language Models with Visual Context Record MemoryWithdrawn2.00
[PDF]Distributed Evidence Memory: Deferring Irreversible Decisions for Reliable Long-Term MemoryWithdrawn2.00
[PDF]MemReq: Contract-Conditional Requirement Profiles for Diagnosing Agent Memory FailuresWithdrawn1.00
[PDF]MemState: Dynamic Memory State Graph Construction and Agentic State Graph RetrievalWithdrawn1.67