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819 results for “keyword:"reward"” in ICLR 2027. 154 withdrawn or desk rejected listed apart.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]Agreement Is Not Validity: A Preregistered Audit of Human-Anchored LLM-Judge Evaluation▼1.2k1.67
[PDF]When Agents Choose What to Observe: BEATS – Answer-Free Test-Time Selection for Verifiable-Reward Agents▼1.2k1.67
[PDF]PrefGeo: Generalizing Preference Learning Across Contexts via Geometric Reward Factorization▲5.4k3.00
[PDF]The Solution Is the Supervision: Learning to Verify Reasoning without Human Step Labels▼5.8k2.33
[PDF]Do Process Reward Models Fail to Detect Errors, or Fail to Decide? A Controlled Study of Operating Points▲5.4k3.00
Withdrawn or desk rejected (154)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