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5,246 results for “keyword:"agent"” in ICLR 2027. 1,220 withdrawn or desk rejected listed apart.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]Self-Improvement Needs Attribution: Dependency-Aware Causal Memory for Long-Horizon Mobile GUI Agents▼1.2k3.00
[PDF]Beyond Global Symmetry: State-Conditioned Graph-Structured Partial Equivariance for Reinforcement Learning▲4.6k3.00
[PDF]Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution▼4.3k2.00
[PDF]Self-Regression-Test:Continuous Integration for Self-Evolving Agents That Rewrite Their Own Skills▲5.4k3.00
[PDF]Failure Migration in GUI Agents: Outcome Churn and the Trade-offs of Reflective Recovery▼1361.33
[PDF]What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media▲6.6k3.33
[PDF]Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents▼4.3k2.00
[PDF]Explaining and Calibrating Dynamically Orchestrated LLM MAS through Stepwise Uncertainty Decomposition▲9.7k2.75
[PDF]Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate▼5.8k2.33
[PDF]RSIBench-Infra: Can Agents Optimize Their Own Training and Inference Infrastructure at Production Scale?▲9.2k2.67
[PDF]DEEPSEARCHDAG: A DAG-STRUCTURED BENCHMARK FOR NODE-LEVEL EVALUATION OF DEEP SEARCH AGENTS▼1361.33
[PDF]Communication Gain and Delay Cost under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learning▼5.8k2.33
[PDF]When Does Multi-Agent Debate Backfire? A Predictable and Preventable Failure Mode of Heterogeneous LLM Debate▼1611.50
Withdrawn or desk rejected (1,220)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