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5,245 results for “keyword:"agent"” in ICLR 2027. 1,221 withdrawn or desk rejected listed apart.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]FinancialAuditBench: Benchmark Construction under Differential Privacy Using Real-World Priors▼1.2k3.00
[PDF]Learn from Weaknesses: Student-aware Domain Specialization for Small Computer-Use Agents▼4.3k2.00
[PDF]Grounded in Hallucination: Belief-Guided Embodied Task Planning in Dynamic, Uncertain Environments▲8.9k2.75
[PDF]Rome Wasn’t Built in One Turn: Replay-Grounded Reward Signals for Long-Horizon Freeciv Agents▼4.3k2.00
[PDF]GPUPhysBench: Benchmarking Coding Agents for Correct and Efficient GPU Physics Simulation▲3892.67
[PDF]Reinforcing The World’s Edge: A Continual Learning Problem In The Multi-Agent-World Boundary▲3892.67
[PDF]Adversarial Self-Play for Scientific-Computing Agents: An Arena Where a Model Writes Finite-Element Problems It Cannot Solve▼1.2k1.67
[PDF]Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent▲4.6k3.00
[PDF]Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning▼4.3k2.00
[PDF]When Should AI Chime In? Benchmarking Timely Contribution of Proactive Agents in Multi-Party Chat▼5.9k2.33
[PDF]Understand Once, Retrieve Many Times: SAADI for Single-Pass Retrieval of Distributed Evidence in Long Documents▲9.2k2.67
[PDF]Interpreting Sparse Autoencoder Features in Cytometry Foundation Models through In Silico Perturbations▼4.3k2.00
Withdrawn or desk rejected (1,221)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