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819 results for “keyword:"reward"” in ICLR 2027. 154 withdrawn or desk rejected listed apart.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]Value-Informed Schedule Trimming for Accelerated Sequential Monte Carlo Guidance in Discrete Diffusion▼4.3k2.00
[PDF]CARVE: Coordinating Imitation and Exploration through Reward Variance for LLM Reasoning Post-Training▼1361.33
[PDF]Bridging Candidate Selection and Mean-Shift Guidance for Diffusion Reward Alignment via Linear Noise Ranking▲9.2k2.67
[PDF]Measure First, Then Allocate: Calibrated Rollout Budgets for MCP Agents in Reinforcement Learning▼4.3k2.00
[PDF]DeltaPRM: Rollout-Free Automatic Process Rewards via Answer Likelihood Gain for Retrieval Agents▲5.4k3.00
[PDF]Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning▼1.2k3.00
[PDF]Target Value as Potential: Reward Shaping in Deep Reinforcement Learning by Transferring Prior Knowledge▼1.2k1.67
[PDF]Societal Hacking: Reward Optimisation Amplifies Societal Loophole Exploitation in LLMs▼5.8k2.33
[PDF]Adaptive Contrastive Self-Play for Regime-Aware Reinforcement Learning Fine-Tuning of Language Models▼4.3k2.00
[PDF]A Claim Is Not a Measurement: Compliance Claims Change What LLM Evaluators Verify and Accept▲3.0k2.33
[PDF]PeerCredit: Cross-Prompt Token Credit Assignment for Reinforcement Learning with Verifiable Rewards▲5.4k3.00
[PDF]The Vanishing Middle: Reinforcement Learning Erases the Uncertain Category in Ordinal Classification▲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Withdrawn or desk rejected (154)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