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
37 results for “keyword:"reward design"” in ICLR 2027. 6 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learn to Sell, Not What to Sell: Dualistic Self-Evolution (DSE) of LLM Sales Agents with Human Nature as Reward (HNR)▼4.3k2.00
[PDF]R-Split: Population-Level Reasoning over Reward Mechanisms for Automated Reward Design with LLMs▼4.3k2.00
[PDF]Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics▲5103.00
[PDF]GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction▼1361.33
[PDF]Learning Cyber Defense with Limited Interaction: An Empirical Study of Reflective Prompt Optimization▼1.2k1.67
[PDF]Count the constraints, not the tests: verifier diversity governs reinforcement learning from execution feedback▼1.3k1.75
[PDF]RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models▼4.3k2.00
[PDF]Let Intuition Teach Deliberation: Rewarding Prefix Success Potential in Reasoning Models▼4.3k2.00
[PDF]Beyond Scripted Search: Sample-Efficient Reward Discovery via Agentic Black-box Optimization▲1.7k3.33
[PDF]Reward Reasoning for Its Gain over a Snap Judgment: Inverse-RL Cold Start of GUI Agents with an Adversarial Critic▲5.4k3.00
[PDF]MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models
[PDF]GeoVR: Structured Execution Rewards for Reinforcement Learning in Geospatial Code Generation▲3.0k2.33
[PDF]RL-Trained Crop-and-Zoom Is Often Decorative: Pixel Budgets, Protocol Costs, and Causal Credit▼4.5k2.67
[PDF]Termination Calibration Recovers Answers That Reasoning Models Compute but Never Express▼4.5k2.67
Withdrawn or desk rejected (6)
[PDF]Verifier-Induced Strategy Collapse: Family-Correlated False Negatives Eliminate Valid Strategies While Capability Metrics ImproveDesk rejected