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
5,243 results for “keyword:"agent"” in ICLR 2027. 1,223 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training▲9.2k2.67
[PDF]Agent Error Dataset: Scaling 50,000 Error–Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training▼5.9k2.33
[PDF]Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents▲3872.67
[PDF]Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization▼4.3k2.00
[PDF]AgentDriftBench: Measuring Adaptation Dynamics of LLM Agents under Mid-Evaluation Environment Drift▼1361.33
[PDF]Benchmarking and Evaluating Implicit Biases in Single- and Multi-Agent Language Models▼5.9k2.33
[PDF]Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twin Construction▼1.2k1.67
[PDF]AutoBCI: Forecast-Guided Agentic Neural Architecture Discovery for EEG-Based Brain–Computer Interfaces▼5.9k2.33
[PDF]PhysicianUIBench: Benchmarking Computer-Use Agents through a High-Fidelity EHR Interface▼4.5k2.25
[PDF]CVE-Bench Hard: Rigorous Evaluation of AI Agents for Identifying and Exploiting Complex Web Application Vulnerabilities▼4.5k2.67
[PDF]A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering▲3.9k1.67
[PDF]LMSysDojo: Building Scalable Analytical Agents for Optimizing Complex LLM Serving Systems▲1.7k3.33
[PDF]AI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents▼1361.33
Withdrawn or desk rejected (1,223)
[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