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
4,860 results for “keyword:"lm"” in ICLR 2027. 941 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]UniRel: Relation-Centric Knowledge Graph Question Answering with RL-Tuned LLM Reasoning▲3892.67
[PDF]Beyond Answer Preservation: Scientific Evidence Minimization for Private LLM Reasoning▼5.9k2.33
[PDF]OppoMem: An Opponent-Aware Memory Framework for LLM Agents Evolving in Strategic Games▼4.5k2.67
[PDF]PraxiScene: Benchmarking Agent Social Agency in Generated Open-Goal Interactive Scenarios▲3.0k2.50
[PDF]MedicalPressureBench: Evaluating Care Pathway Integrity of Medical Agents Under Workplace Pressure▼4.3k2.00
[PDF]AgentEvolve: LLM-Guided Multi-Objective Evolutionary Optimization for Expensive Black-Box Design Problems▲3.0k2.33
[PDF]RAF: RUBRICS AUTO-GENERATION FRAMEWORK FOR AUDITABLE EVALUATION OF LONG-HORIZON LLM AGENTS▼4.3k2.00
[PDF]Continuous Oversight, Selective Deliberation: Event-Triggered Metareasoning for Judgment Revision▲6.1k2.00
[PDF]1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World▼5.9k2.33
[PDF]Parameters as Agentic Memory: Internalizing Long-Horizon Memories for Efficient LLM Agents▲3.0k2.33
[PDF]HyperPlan: Modeling High-Order Task Relations with Constraint Hypergraphs for LLM Planning▼5.9k2.33
[PDF]Beyond Confidence: Evidence-Guided Selective Answer Revision for Frozen Vision-Language Model▼1611.60
[PDF]OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations▼4.3k2.00
[PDF]True Quotes, False Impressions: A Benchmark for Adversarial Extractive Summarization on Long-Document Classification▼4.3k2.00
[PDF]ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Models▼1.3k1.75
[PDF]Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning▼4.3k2.00
[PDF]MolDeTox: Evaluating Language Model’s Stepwise Fragment Editing for Molecular Detoxification▼4.3k2.00
Withdrawn or desk rejected (941)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]-Bench: Benchmarking Proactive Speech Interaction with Full-Duplex Conversational AIDesk rejected