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
5,245 results for “keyword:"agent"” in ICLR 2027. 1,221 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What Makes Agents Effective for Scientific Design? A Controlled Evaluation with Scientific Foundation Model Tools▼5.9k2.33
[PDF]Measure First, Then Allocate: Calibrated Rollout Budgets for MCP Agents in Reinforcement Learning▼4.3k2.00
[PDF]Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models▼5.9k2.33
[PDF]VeriBench-Infinity: Detecting Verification Hallucinations, Valid Proofs of the Wrong Program▼4.3k2.00
[PDF]DeltaPRM: Rollout-Free Automatic Process Rewards via Answer Likelihood Gain for Retrieval Agents▲5.4k3.00
[PDF]SWE-RedAgent: Adaptive Red-Teaming of Coding Agents via Utility-Preserving Vulnerability Injection▼1.2k3.00
[PDF]RecoAtlas: A Benchmark and RL Environment for LLM Recommendation Agents Optimizing Set-Level Utility▼4.3k2.00
[PDF]A Risk-Bounded Gate for Self-Improving Agents: Selecting Modifications as a Mean–Variance Knapsack▼1361.33
Withdrawn or desk rejected (1,221)
[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