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5,246 results for “keyword:"agent"” in ICLR 2027. 1,220 withdrawn or desk rejected listed apart.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]From Case Feedback to Auditable Memory: Context Evolution for Complete Blood Count-Based Risk-Oriented Reasoning▼1361.33
[PDF]PROTEAN: Beyond De Novo Generation — Can LLM Agents Perform Text-Guided Protein Structure Editing?▲5.4k3.00
[PDF]BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systems▼4.3k2.00
[PDF]PULSEBench: Personalized Understanding of Longitudinal Sensor Evidence for Wearable Health Reasoning▼4.3k2.00
[PDF]EvoTrace: Learning to Evolve Scientific Hypotheses from Trajectories of Agentic Symbolic Regression▲3.0k2.33
[PDF]CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement▼4.5k2.67
[PDF]What Should Embodied Agents Remember? Evaluating and Benchmarking Memory Modality for Embodied Agents▼4.5k2.67
[PDF]ProContract: Decoupling Responsibility and Progress from the Harness in Long-Horizon Agents▼1.3k1.75
[PDF]PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides▼4.3k2.00
[PDF]Discover and Internalize: A Continual Co-Evolving Training Loop for Self-Improvement Agents▼1.2k1.67
[PDF]Doing More with Less Tokens: Hierarchical Reinforcement Learning for Efficient Coding Agents▲3.0k2.40
[PDF]SteerDistill: Quantizing LLM Agents via Online Teacher-Steered Trajectory Distillation▼4.5k2.67
[PDF]GeneralsArena: Evaluating End-to-End Agent Systems through Persistent Real-Time Competition▲3.0k2.33
[PDF]StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding▼5.8k2.33
Withdrawn or desk rejected (1,220)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