{"total":37,"rows":[{"id":"2509.15194","title":"Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation","created":"2025-09-18","cited_by_count":45,"area":null},{"id":"2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","created":"2025-09-29","cited_by_count":42,"area":null},{"id":"2509.07430","title":"The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward","created":"2025-09-09","cited_by_count":37,"area":null},{"id":"2508.11356","title":"ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism","created":"2025-08-15","cited_by_count":36,"area":null},{"id":"2512.02472","title":"Guided Self-Evolving LLMs with Minimal Human Supervision","created":"2025-12-02","cited_by_count":35,"area":null},{"id":"2505.20282","title":"One-shot Entropy Minimization","created":"2025-05-26","cited_by_count":32,"area":null},{"id":"2508.14496","title":"Semantic Energy: Detecting LLM Hallucination Beyond Entropy","created":"2025-08-20","cited_by_count":18,"area":null},{"id":"2509.14234","title":"Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision","created":"2025-09-17","cited_by_count":18,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2506.10139","title":"Unsupervised Elicitation of Language Models","created":"2025-06-11","cited_by_count":11,"area":null},{"id":"2509.16591","title":"Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature","created":"2025-09-20","cited_by_count":11,"area":null},{"id":"2602.07729","title":"Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2508.21188","title":"Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions","created":"2025-08-28","cited_by_count":6,"area":null},{"id":"2510.10223","title":"You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2605.09920","title":"Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2510.01527","title":"Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2601.15690","title":"From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2509.25204","title":"Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2605.07244","title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2607.14614","title":"Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2608.24136","title":"Steering Recurrent Reasoners at Inference Time with Readout Feedback","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2508.12086","title":"J6: Jacobian-Driven Role Attribution for Multi-Objective Prompt Optimization in LLMs","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2510.20635","title":"Why Did Apple Fall: Evaluating Curiosity in Large Language Models","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2601.17728","title":"Unsupervised Elicitation of Moral Values from Language Models","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2601.18588","title":"Stability as a Liability:Systematic Breakdown of Linguistic Structure in LLMs","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2601.22532","title":"Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2601.22786","title":"Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.12875","title":"Test-time RL alignment exposes task familiarity artifacts in LLM benchmarks","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.08454","title":"Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.20369","title":"DEL: Digit Entropy Loss for Numerical Learning of Large Language Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.30844","title":"Fine-Tuning Improves Information Conveyance in Language Models","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.01436","title":"Learning from Saturated Data: Signals Beyond Correctness for LLM Training","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.02339","title":"Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.02510","title":"Online Safety Monitoring for LLMs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.24982","title":"Unsupervised Post-Training of Foundation Models: A Survey","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.30572","title":"Entropy Regularization: A Free Correction to Cross-Entropy for Verified Demonstrations","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.15084","title":"Self-Evolving Visual Agent via Margin Reward","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}