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
5,246 results for “keyword:"agent"” in ICLR 2027. 1,220 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]The Environment Knows Why: Bidirectional Self-Distillation from Augmented Tool Feedback for Agentic RL▲2623.67
[PDF]When and Why Do Agents Become Unsafe? A Trajectory-Aware Benchmark for Multi-Turn Agent Safety Evaluation▲3952.67
[PDF]Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents▼5.1k2.60
[PDF]Interface-Induced Trajectory Censoring: When Tool-Call Interfaces Distort Evaluation and RL Experience▼5.3k1.33
[PDF]TIDE: Teacher-Student Transition via Informative Distillation and Exploration for Agentic RL▼4.3k2.00
[PDF]Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Memory Requirements▲5103.00
[PDF]PowerMarketJax: A JAX Benchmark Suite for Multi-Agent Reinforcement Learning in Power Markets▼5.8k2.33
[PDF]RealControlBench: A Comprehensive Benchmark for Fine-Grained LLM and LLM Agent steer in the Wild▼5.8k2.33
[PDF]The Opponent Learns Too: Alternating Adversarial Training for Stronger Conversational Agents▼4.5k2.25
[PDF]Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy▲6.1k2.00
[PDF]What Retrieval Buys Depends on Who Reads: Splitting Multi-Hop RAG Accuracy into Assembly and Reading▼1.2k1.67
[PDF]SCOPE: Scaling Counterfactual, Observation-Preserving Environment Families for Terminal Agents▼4.3k2.00
[PDF]Causal Experience Instantiation: Grounding Procedural Memory with Temporal Graphs for Tool-Use Agents▲5103.00
Withdrawn or desk rejected (1,220)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected
[PDF]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00