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
3,190 results for “keyword:"reinforcement"” in ICLR 2027. 649 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Knowing When to Defer: Training Language Models to Generate an Answer and Its Confidence Level Together for the Thresholds That Matter▼1361.33
[PDF]BeaconAgent: Learning Capability-Aware Help-Seeking Policies for Small Language Model Agents▲3942.67
[PDF]Decision-Centric Reinforcement Learning over Promising Tokens for Large Language Model Reasoning▲6.1k2.00
[PDF]LeDreamer: Bridging the Understanding of Representation Collapse Between JEPA and Sample-Efficient World Models▼5.8k2.33
[PDF]Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation▼5.8k2.33
[PDF]What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization▲3942.67
[PDF]When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards▼1.2k1.67
[PDF]A Falsification Study of Coupled-Constraint Telemetry Diagnostics in Multi-Agent Learning▼1361.33
[PDF]Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila▲3.0k2.33
[PDF]RELACE: RETROSPECTIVE LIKELIHOOD-BASED ACTION CREDIT ESTIMATION FOR LONG-HORIZON LANGUAGE AGENTS▼1.2k1.67
[PDF]Beyond Solo and Consistency: Vindicating Multi-Agent Debate through Conditional Progressive Pruning▼1361.33
[PDF]WUIRL: Reconstructing Wildfire Structure Ignition in the Wildland–Urban Interface with Reinforcement Learning▲19k2.33
[PDF]STRATA: Preserving Rare Solution Strategies in Reinforcement Learning with Verifiable Rewards▼1361.33
[PDF]When LoRA Rank Matters in RLVR: Saturation-Gated Scaling and Off-Principal Initialization▼1361.33
[PDF]ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning▲5.4k3.00
[PDF]Reinforcing LLM Latent Reasoning with Contextual Loops through On-Policy Flow-Map Self-Distillation▼1.2k1.67
Withdrawn or desk rejected (649)
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected
[PDF]What Should I Try Next? Decision-Relevant Counterfactual Information Gain for Active World ModelsWithdrawn1.00
[PDF]Never Stop Rewiring: Safe Continual Reinforcement Learning on Non-Resetting GraphsWithdrawn1.33
[PDF]Recoverable Coordination Distillation for Decentralized Multi-Agent Reinforcement LearningWithdrawn1.67