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5,246 results for “keyword:"agent"” in ICLR 2027. 1,220 withdrawn or desk rejected listed apart.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]Harness Evolution as Learning: Approximation, Generalization, and Optimization Limits of Self-Improving Personal Agents▼4.3k2.00
[PDF]Dormant Agent: Stealthy Cross-Agent Attacks in VLM-Based Multi-Agent Systems via Emotion Steering▲3952.67
[PDF]FedGOTA: Towards Effective Federated Multi-Agent Collaboration via Graph Optimal-Transport Alignment▲9.2k2.67
[PDF]EarthVerse: Benchmarking Scientific Agents across Dynamic Earth Systems and Natural Hazards▼4.3k2.00
[PDF]PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning▲432.75
[PDF]Can LLM Agents Communicate Without Autoregression? Thought Blocks for Latent Multi-Agent Collaboration▲5.4k3.00
[PDF]CIT-Mem: Counterfactual Intervention Training for Evidence-Grounded Memory Policies in Long-Horizon LLM Agents▼1.2k1.67
[PDF]Towards Reliable Financial Agents: Mitigating Financial Hallucinations through Evidence-Grounded Execution and Verified Experience▲3.0k2.33
[PDF]Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence▼4.3k2.00
[PDF]Your Best Retriever May Not Be Best for Your Reranker: Adaptive Coordination for LLM Recommendation Cascades▲3.0k2.33
[PDF]How Harnesses Reshape Agentic Search: Training Stateless Large Reasoning Models for Stateful Search▼1.3k1.75
[PDF]CookBench: Can Digital Agents Actually Cook? A Multimodal Benchmark for Long-Horizon Embodied Planning▼5.9k2.50
Withdrawn or desk rejected (1,220)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