{"total":118,"rows":[{"id":"2507.17746","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","created":"2025-07-23","cited_by_count":366,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.04324","title":"TempFlow-GRPO: When Timing Matters for GRPO in Flow Models","created":"2025-08-06","cited_by_count":97,"area":"lr"},{"id":"2505.14069","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","created":"2025-05-20","cited_by_count":70,"area":"rag"},{"id":"2505.15034","title":"RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning","created":"2025-05-21","cited_by_count":40,"area":"lr"},{"id":"2509.00676","title":"LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model","created":"2025-08-31","cited_by_count":35,"area":"mllm"},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","cited_by_count":31,"area":null},{"id":"2509.03403","title":"Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training","created":"2025-09-03","cited_by_count":29,"area":"alignment"},{"id":"2508.19229","title":"StepWiser: Stepwise Generative Judges for Wiser Reasoning","created":"2025-08-26","cited_by_count":28,"area":null},{"id":"2509.23738","title":"GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks","created":"2025-09-28","cited_by_count":26,"area":"alignment"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2505.19640","title":"Interleaved Reasoning for Large Language Models via Reinforcement Learning","created":"2025-05-26","cited_by_count":21,"area":"lr"},{"id":"2506.15196","title":"HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges","created":"2025-06-18","cited_by_count":21,"area":null},{"id":"2601.03555","title":"SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models","created":"2026-01-07","cited_by_count":21,"area":"alignment"},{"id":"2506.16507","title":"Robust Reward Modeling via Causal Rubrics","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2510.23038","title":"Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning","created":"2025-10-27","cited_by_count":17,"area":"lr"},{"id":"2512.03109","title":"E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing","created":"2025-12-02","cited_by_count":17,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2508.04088","title":"GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning","created":"2025-08-06","cited_by_count":14,"area":"lr"},{"id":"2601.14209","title":"InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning","created":"2026-01-20","cited_by_count":14,"area":"lr"},{"id":"2509.23250","title":"Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned","created":"2025-09-27","cited_by_count":13,"area":"lr"},{"id":"2511.09586","title":"Environment Scaling for Interactive Agentic Experience Collection: A Survey","created":"2025-11-12","cited_by_count":13,"area":"agents"},{"id":"2512.07461","title":"Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning","created":"2025-12-08","cited_by_count":12,"area":"lr"},{"id":"2603.00656","title":"InfoPO: Information-Driven Policy Optimization for User-Centric Agents","created":"2026-02-28","cited_by_count":12,"area":"agents"},{"id":"2507.23317","title":"Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner","created":"2025-07-31","cited_by_count":11,"area":"lr"},{"id":"2601.20209","title":"Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning","created":"2026-01-28","cited_by_count":11,"area":"agents"},{"id":"2604.10701","title":"Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning","created":"2026-04-12","cited_by_count":11,"area":null},{"id":"2509.25598","title":"Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic Tasks","created":"2025-09-29","cited_by_count":10,"area":"agents"},{"id":"2510.00492","title":"Rethinking Reward Models for Multi-Domain Test-Time Scaling","created":"2025-10-01","cited_by_count":10,"area":"lr"},{"id":"2511.01191","title":"Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning","created":"2025-11-03","cited_by_count":10,"area":"lr"},{"id":"2505.13346","title":"J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization","created":"2025-05-19","cited_by_count":9,"area":"lr"},{"id":"2505.15960","title":"Efficient PRM Training Data Synthesis via Formal Verification","created":"2025-05-21","cited_by_count":8,"area":"lr"},{"id":"2505.19706","title":"Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2508.16665","title":"Trust but Verify! A Survey on Verification Design for Test-time Scaling","created":"2025-08-20","cited_by_count":8,"area":"lr"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2507.15024","title":"RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback","created":"2025-07-20","cited_by_count":7,"area":"lr"},{"id":"2508.15202","title":"Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models","created":"2025-08-21","cited_by_count":7,"area":"lr"},{"id":"2601.10306","title":"Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning","created":"2026-01-15","cited_by_count":7,"area":"lr"},{"id":"2604.22937","title":"AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs","created":"2026-04-24","cited_by_count":7,"area":null},{"id":"2606.09071","title":"REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces","created":"2026-06-08","cited_by_count":7,"area":"agents"},{"id":"2505.17225","title":"Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models","created":"2025-05-22","cited_by_count":6,"area":"lr"},{"id":"2509.16548","title":"SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning","created":"2025-09-20","cited_by_count":6,"area":"lr"},{"id":"2512.04558","title":"On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference","created":"2025-12-04","cited_by_count":6,"area":"lr"},{"id":"2601.14691","title":"Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation","created":"2026-01-21","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2510.06217","title":"TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2601.22642","title":"Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2604.24198","title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","created":"2026-04-27","cited_by_count":5,"area":"lr"},{"id":"2506.15498","title":"SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling","created":"2025-06-18","cited_by_count":4,"area":"lr"},{"id":"2509.25409","title":"From Faithfulness to Correctness: Generative Reward Models that Think Critically","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2510.09354","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2603.16253","title":"Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2603.28135","title":"CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning","created":"2026-03-30","cited_by_count":4,"area":"lr"},{"id":"2605.29116","title":"Beyond Consensus: Trace-Level Synthesis in Mixture of Agents","created":"2026-05-27","cited_by_count":4,"area":"agents"},{"id":"2605.30451","title":"VeriGate: Verifier-Gated Step-Level Supervision for GRPO","created":"2026-05-28","cited_by_count":4,"area":"lr"},{"id":"2607.09153","title":"KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling","created":"2026-07-10","cited_by_count":4,"area":"lr"},{"id":"2506.00845","title":"Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2511.11233","title":"STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models","created":"2025-11-14","cited_by_count":3,"area":"lr"},{"id":"2601.03321","title":"HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize","created":"2026-01-06","cited_by_count":3,"area":"lr"},{"id":"2602.24110","title":"Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2606.00440","title":"SDR: Set-Distance Rewards for Radiology Report Generation","created":"2026-05-30","cited_by_count":3,"area":"lr"},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2608.00017","title":"Memory Reward Inflation in Self-Improving LLM Agents","created":"2026-06-29","cited_by_count":3,"area":"agents"},{"id":"2507.12759","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-07-17","cited_by_count":2,"area":"lr"},{"id":"2512.03244","title":"ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground Truth","created":"2025-12-02","cited_by_count":2,"area":"lr"},{"id":"2601.04674","title":"PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2601.12748","title":"Towards Robust Process Reward Modeling via Noise-aware Learning","created":"2026-01-19","cited_by_count":2,"area":"lr"},{"id":"2601.14304","title":"Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding","created":"2026-01-18","cited_by_count":2,"area":null},{"id":"2602.01485","title":"Predicting and improving test-time scaling laws via reward tail-guided search","created":"2026-02-01","cited_by_count":2,"area":"lr"},{"id":"2602.05242","title":"EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.08489","title":"Beyond Correctness: Learning Robust Reasoning via Transfer","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2603.08999","title":"Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoning","created":"2026-03-09","cited_by_count":2,"area":"lr"},{"id":"2603.24780","title":"Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2603.27977","title":"SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology","created":"2026-03-30","cited_by_count":2,"area":"lr"},{"id":"2604.17912","title":"Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2604.19656","title":"Pause or Fabricate? Training Language Models for Grounded Reasoning","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2605.17609","title":"Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification","created":"2026-05-17","cited_by_count":2,"area":"lr"},{"id":"2605.17626","title":"Verifier-Guided Code Translation via Meta-Step Decoding","created":"2026-05-17","cited_by_count":2,"area":"lr"},{"id":"2605.18871","title":"Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning","created":"2026-05-15","cited_by_count":2,"area":"lr"},{"id":"2605.30712","title":"ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents","created":"2026-05-29","cited_by_count":2,"area":"agents"},{"id":"2606.12916","title":"MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2607.10139","title":"LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning","created":"2026-07-11","cited_by_count":2,"area":"lr"},{"id":"2608.15797","title":"KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving","created":"2026-08-16","cited_by_count":2,"area":"lr"},{"id":"2509.24351","title":"From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2510.20188","title":"TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning","created":"2025-10-23","cited_by_count":1,"area":"lr"},{"id":"2602.02863","title":"\"I May Not Have Articulated Myself Clearly\": Diagnosing Dynamic Instability in LLM Reasoning at Inference Time","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.04145","title":"Training Data Efficiency in Multimodal Process Reward Models","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2602.06475","title":"Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2602.10224","title":"Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2604.13197","title":"Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2604.23366","title":"GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs","created":"2026-04-25","cited_by_count":1,"area":"agents"},{"id":"2605.18851","title":"STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.29656","title":"TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"id":"2606.09078","title":"The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning","created":"2026-06-08","cited_by_count":1,"area":"lr"},{"id":"2606.24124","title":"VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2607.02073","title":"Evidence-State Rewards for Long-Context Reasoning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2609.03342","title":"Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards","created":"2026-09-03","cited_by_count":1,"area":"lr"},{"id":"2609.36641","title":"Inducing Process Supervision from Outcome-Only Reinforcement Learning","created":"2026-09-29","cited_by_count":1,"area":"lr"},{"id":"2609.39982","title":"Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents","created":"2026-09-30","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}