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
819 results for “keyword:"reward"” in ICLR 2027. 154 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Guiding Where the Antibody Binds: Amortised Cross-Subsample Particle Steering for Antibody–Antigen Co-Folding▼5.8k2.33
[PDF]Adversarial Nonlinear Semi-Bandits: Hidden Interactions and Amplitude-Sensitive Regret▲5.4k3.00
[PDF]Rich Outcomes, Selective Constraints: Goal Overspecification in Offline Goal-Conditioned Learning▲9.2k2.67
[PDF]Mentor-Baseline Implicit Imitation Learning from a Single Action-Free Mentor Trajectory▼5.8k2.33
[PDF]Efficient Multi-Agent Reinforcement Learning under Sparse Binary Team Rewards with Few Suboptimal Prior Trajectories▲3.8k2.50
[PDF]Annotate or Filter? The Redundancy–Rescue Mechanism and Phase Boundaries in LLM Fusion Pipelines▲5.4k3.00
[PDF]RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models▼4.3k2.00
[PDF]Typed-Reward-Aware Credit Estimation and Routing for Multi-Reward Agentic Reinforcement Learning▲3.0k2.33
[PDF]SAME SCORE, DIFFERENT OUTCOMES: REWARD INTERFACES SHAPE IN-CONTEXT REINFORCEMENT LEARNING▼4.3k2.00
[PDF]Don't Waste Failures: Leveraging Failure Length Signals for Discriminative Thresholds in Efficient Reasoning▲9.2k2.67
[PDF]Reinforcement Learning in Infinite State Spaces: Convergence Guarantees via Stable Exploration▲3952.67
[PDF]ArtiVidRM: Verifiable Artifact-as-Rubric Reward Modeling for Explicit Quality Articulation in Video Generation▲3952.67
[PDF]PREDICTIVE, NOT REACTIVE: TASK FILTERING FOR COMPUTE-EFFICIENT GRPO TRAINING OF CODE AGENTS▼4.3k2.00
[PDF]The Router Is Already in the ARMs: Disagreement-Guided Multi-Objective Test-Time Alignment for LLMs▲14k3.00
[PDF]BlendPO: Controlling Guidance Strength in Reinforcement Learning without Changing Guidance Content▲9.2k2.67
Withdrawn or desk rejected (154)
[PDF]Auditing Reward-Model Selection on Tool Trajectories: Identification, Policy Utility, and Natural TransferWithdrawn1.67
[PDF]Verifier-Induced Strategy Collapse: Family-Correlated False Negatives Eliminate Valid Strategies While Capability Metrics ImproveDesk rejected
[PDF]Reflection Rewards Pay for Deferral: Capability-Aware Rewards for Reflective RLDesk rejected3.00