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
94 results for “keyword:"reward hacking"” in ICLR 2027. 19 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Reproducing, Analyzing, and Detecting Reward Hacking in Rubric‑Based Reinforcement Learning▲3952.67
[PDF]StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents▲3.0k2.33
[PDF]STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking▼4.3k2.00
[PDF]Technique Awareness as an Alignment Risk: Model Familiarity of Inoculation Prompting Weakens its Effect▼1.2k3.00
[PDF]Whether or Where? Tail Calibration Signals Finite-Budget Reward Hacking in Best-of-N Selection▼1.2k1.67
[PDF]High Reward, Wrong Sequences: Reward-Hacking Resistant Discrete Diffusion for 5’UTR Design▼1361.33
[PDF]RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback▲5103.00
[PDF]On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models▼5.8k2.33
[PDF]Goodhart’s Law in Performance Benchmarks: Measuring and Mitigating Software Overoptimization▼4.3k2.00
[PDF]EvoRS: On-Policy Self-Evolution of Reward Systems for Open-Ended Reinforcement Learning▼4.5k2.67
[PDF]Replication Is Not Specificity: Negative Controls for Representation-Based Reward-Hacking Detection▼1361.33
[PDF]How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review▲3.0k2.40
[PDF]Pressure Is Not Enough: A Causal Test of Whether Optimization Induces Encoded Chain-of-Thought▼1.2k1.67
[PDF]Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack▼4.3k2.00
[PDF]Normal Fréchet Drift: Measuring Post-Training Departure from Pretrained Reference Manifold▲13k2.33
Withdrawn or desk rejected (19)
[PDF]Verifier-Induced Strategy Collapse: Family-Correlated False Negatives Eliminate Valid Strategies While Capability Metrics ImproveDesk rejected
[PDF]False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search AgentsDesk rejected3.00
[PDF]MedFrame-R1: Reward Gating & Informative Sampling for Medical Multimodal ReasoningWithdrawn1.67
[PDF]Residual Fusion for Cold-Start Matrix Completion and Reward-Model-Guided Generation: A Case Study in Drug Response Prediction with Specification GamingDesk rejected
[PDF]Fooled at Probe Time, Ignored at Training Time: The Mechanism and Exploitation Boundary of Verifier Susceptibility in RLDesk rejected