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
4,861 results for “keyword:"lm"” in ICLR 2027. 940 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin▲14k3.00
[PDF]What Do Benchmarks Measure? Discovering Benchmark Demands and Grounding System Capabilities▲20k2.67
[PDF]EvoMO-SR: Multiobjective LLM-based Evolution of Symbolic Expressions with substructure guidance▼1.2k1.67
[PDF]BranchWise: A Path Is Not a Policy — Unfolding Successful Trajectories into Model-Tailored Decision Boundaries▲9.2k2.67
[PDF]Finding Root Causes, Not Symptoms: A Mechanism and Method for Agent Failure Attribution▼5.8k2.33
[PDF]Rambling on Repeat? Exact First-Exit Laws and Minimal Intervention for Verbatim LLM Loops▼1611.50
[PDF]SUE-Mem: Logic-Guided Overlapping Event Storylines for Long-Term Conversational Memory▼5.8k2.33
[PDF]GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets▼5.8k2.33
[PDF]PostTrainBench-Pro: How Well Can AI Agents Post-Train Domain-Level Capabilities under Controlled Compute?▲5.4k3.00
[PDF]GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory▲3912.67
[PDF]Agentic-OPD: Recovering Forgotten Agent Capabilities via On-Policy Distillation for Long-Horizon Tasks▲6.1k2.00
[PDF]SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery▼4.5k2.67
[PDF]Representation and Motivation Are Superadditive: Unlocking Exploration for LLM Agents in Structured Search▲6.1k2.00
[PDF]TTRSD: Test-Time Reinforcement Learning with Self-Distillation for Vision-Language Models▲3.7k2.50
Withdrawn or desk rejected (940)
[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