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
9,712 results for “keyword:"em"” in ICLR 2027. 2,420 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[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▼1351.33
[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]CHIP: One Chi-Squared Ball for Both Errors of Reinforcement Learning in Large Language Models▲5.4k3.00
[PDF]When Does Memory Become Capability? Agent Self-Improvement through Memory Evolution and Consolidation▲5.4k3.00
[PDF]DESIGN THEFEEDBACK, NOTJUST THEREWARD: ENVIRONMENTS FOROPEN-ENDED REINFORCEMENT LEARNING▼4.3k2.00
[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]Invariant Imagination: Learning What Should Not Change the Future in JEPA World Models▼4.3k2.00
[PDF]SCOUT: State-Conditional Counterfactual Privilege Distillation for Agentic Reinforcement Learning▲9.2k2.67
[PDF]Right Answers for the Right Reasons? Bridging Reasoning Utility and Visual Dependency in Multimodal Reinforcement Learning▲3792.67
[PDF]Modeling Continuous Spatio-Temporal Disease Evolution for Longitudinal Radiology Report Generation▼13k2.00
[PDF]Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geometry Problem Solving▲5083.00
[PDF]An Agent Is More Than Its Model: Controlled Safety Measurement Across CLI Model–Harness Configurations▲3.0k2.33
[PDF]ReDU-IR: Reconstructible Feature Decomposition and State Complementary Updating for All-in-One Blind Image Restoration▲5083.00
[PDF]Investor-Specific Multi-Objective Preference Alignment for Personalized Portfolio Optimization▲3.0k2.33
Withdrawn or desk rejected (2,420)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33