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
4,863 results for “keyword:"lm"” in ICLR 2027. 938 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Compiled Agency: Coding Agents as Game AI Researchers — from a Roguelike to StarCraft II and Civilization▲9.2k2.67
[PDF]Learning What to Check: Process Supervision with Artifact-Grounded Verification for Scientific Agents▼1361.33
[PDF]CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents▼4.3k2.00
[PDF]Sinkhorn-DPO: Distributionally Robust Preference Alignment via Entropic Optimal Transport▼1361.33
[PDF]Beyond the Transcript: Detecting Covert Coordination in Latent Multi-Agent Communication▼4.3k2.00
[PDF]Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training▲15k3.33
[PDF]Learning from Late Rewards: Asynchronous Data Synthesis with Realized Learning Utility▼1.3k1.75
[PDF]MIDIAN: Metric-Induced Distributed Agent Networks for Scalable, Adversarially Robust Task Allocation▲3.9k1.67
[PDF]Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams▼1.2k1.67
[PDF]The Butterfly Effect in LLM Social Simulations: From Architecture Sensitivity to Robustness Audits▼4.5k2.67
[PDF]Tool Graph Complexity for LLM Tool-Calling: A Reproducible Benchmark Auditing and Generation Framework▼4.3k2.00
Withdrawn or desk rejected (938)
[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