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5,243 results for “keyword:"agent"” in ICLR 2027. 1,223 withdrawn or desk rejected listed apart.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]Disentangle to Correct: Separating Temporal Structure from Noise in Multi-Agent Reinforcement Learning▼1.2k1.67
[PDF]HAD²RL: Heterogeneous-Agent Dense Reinforcement Learning for Adversarial Failure Search of Detect-and-Avoid Systems▲1.7k3.33
[PDF]From Skills to Stages: Stage-Aware Graph Retrieval for Relevant Skills in Large-Scale Agent Skill Libraries▼4.3k2.00
[PDF]V-CUES: Improving Multimodal Search Agents by Centering Visual-Cue Utilization via Experience and Skills▼5.9k2.33
[PDF]Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds▲20k2.67
[PDF]TraceGen: Synthesizing Difficulty-Controllable Bugs for Training and Evaluating Code Repair Agents▼1361.33
[PDF]Tracing Paths to Risk: Automated Safety Evaluation for Tool-used Agents via Risk-Path Exploration▼4.3k2.00
[PDF]AlphaGEAR: A Self-Evolving Agent for Alpha Mining via Library-Guided Exploration and Auditable Refinement▼4.3k2.00
[PDF]Coach-Guided Autonomous Reflection Improves Deception and Detection in Multi‑Agent Werewolf Games▼4.3k2.00
[PDF]Beyond Problem-Solving: A Multi-Agent Framework and Pedagogically-Aligned Benchmark for Evaluating LLMs’ Educational Question Generation▼1361.33
[PDF]Episodic Memory Temporal Consistency for Cooperative Multi-Agent Reinforcement Learning▼4.3k2.00
[PDF]OMNE-Engram: A Programmable Knowledge Substrate for Agents with Governed Schema Evolution▼1.2k1.67
[PDF]When Does Memory Become Capability? Agent Self-Improvement through Memory Evolution and Consolidation▲5.4k3.00
[PDF]Beyond Tool Responses: Effect Verification and Residual Recovery under Response–Effect Mismatch▼3.7k2.25
[PDF]HarnessWeaver: Continual Self-Improvement through Task-Conditioned Harness Composition and Model Routing▼4.3k2.00
[PDF]AdvSim2Real: Training Web Agents Against Adaptive Prompt Injection in a Web World Model▲6.1k2.00
[PDF]SCOUT: State-Conditional Counterfactual Privilege Distillation for Agentic Reinforcement Learning▲9.2k2.67
[PDF]An Agent Is More Than Its Model: Controlled Safety Measurement Across CLI Model–Harness Configurations▲3.0k2.33
[PDF]DART: Defense-Aware Red Teaming with a Critical Cue Bank for Open-World Adversarial Evaluation▼5.9k2.33
Withdrawn or desk rejected (1,223)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