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5,246 results for “keyword:"agent"” in ICLR 2027. 1,220 withdrawn or desk rejected listed apart.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]Generalizable Routing to Unseen LLMs via Dynamic Case-Based Memory and Diverse Candidate Sets▼4.3k2.00
[PDF]Certify, Then Act: Formal Safety Certificates for Cooperative LLM Agents in Stochastic Environments▲3942.67
[PDF]Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms▼5.9k2.50
[PDF]PaperRecon: Characterizing Scientific Writing Capabilities of AI Agents through Paper Reconstruction▲9.2k2.67
[PDF]Don't Ask Agents to Do Everything: Selective Agentic Reasoning for Single Image to 3D Scene Generation▲422.75
[PDF]Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference▼4.5k2.67
[PDF]Beyond Memory Construction: Rethinking Memory Access for LLM-based Conversational Agents▼5.8k2.33
[PDF]When Every Rollout Fails: Splicing Learner-Conditioned Options into Long-Horizon Agent RL▼5.8k2.33
[PDF]Collect for Coverage, Replay with Evidence: Adaptive and Efficient On-Policy Distillation for Long-Horizon Agents
[PDF]Positional Coverage Bias: LLM Coverage Judges Verify Where Content Sits, Not Whether It Is There▼4.3k2.00
[PDF]LabCompiler: A Framework for Verifiable Human-Machine Laboratory Execution from Imperfect Protocols▼4.5k2.25
[PDF]Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation▼5.8k2.33
[PDF]Diagnosing Interaction Effects in Pose Prediction: A Cross-Scenario Frequency-Domain Methodology▼1.2k1.67
[PDF]Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic Tasks in Real-World Professional Fields▼5.8k2.33
[PDF]SceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single Images▲5.4k3.00
[PDF]EQUINOX: Benchmarking Natural-Language-to-TLA+ Formalisation by Bounded Trace Equivalence▼4.3k2.00
[PDF]MatBak: Targeted-Behavior Adversarial Attacks on Multiple Reinforcement Agents via Preference-Based Intention Policies▼1.2k1.67
[PDF]Teacher–Student Gaps Are Not Enough: Outcome-Guided On-Policy Distillation for Multi-Turn Autonomous Agents▲5103.00
[PDF]When Does Negotiation Help? Benchmarking Embodied Multi-Agent Collaboration under Successive Task Revisions▼5.9k2.50
[PDF]COCAgent: Chain-of-Causality Multi-Agent Reasoning for Evidence-Based Medical Decision Making▼4.3k2.00
[PDF]Are Research Agents Fooled by Clever Hans? A Benchmark for Proactive Pitfall Detection in Medical Autonomous Research▲3.0k2.33
[PDF]ReelOnce: Adaptive Reference Policy and Evaluation-Driven Hierarchical Refinement for Agentic Multi-Shot Story Video Generation▲3.0k2.33
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