{"total":89,"rows":[{"id":"2603.22446","title":"Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs","created":"2026-03-23","cited_by_count":20,"area":"lr"},{"id":"2601.18744","title":"TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models","created":"2026-01-26","cited_by_count":18,"area":"lr"},{"id":"2601.18577","title":"Self-Refining Video Sampling","created":"2026-01-26","cited_by_count":15,"area":null},{"id":"2510.17472","title":"Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs","created":"2025-10-20","cited_by_count":12,"area":"lr"},{"id":"2511.10788","title":"From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":12,"area":"lr"},{"id":"2512.05105","title":"Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning","created":"2025-12-04","cited_by_count":9,"area":"lr"},{"id":"2605.00365","title":"Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity","created":"2026-05-01","cited_by_count":9,"area":null},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2602.06791","title":"Rare Event Analysis of Large Language Models","created":"2026-02-06","cited_by_count":8,"area":null},{"id":"2602.11683","title":"ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2602.01381","title":"On the Power of (Approximate) Reward Models for Inference-Time Scaling","created":"2026-02-01","cited_by_count":7,"area":"lr"},{"id":"2602.18232","title":"Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning","created":"2026-02-20","cited_by_count":6,"area":"lr"},{"id":"2605.02427","title":"The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling","created":"2026-05-04","cited_by_count":6,"area":null},{"id":"2605.19461","title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","created":"2026-05-19","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":"2601.21484","title":"ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment","created":"2026-01-29","cited_by_count":5,"area":"lr"},{"id":"2604.00375","title":"Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models","created":"2026-04-01","cited_by_count":5,"area":"lr"},{"id":"2604.16453","title":"Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo","created":"2026-04-07","cited_by_count":5,"area":null},{"id":"2607.16097","title":"Understanding Reasoning from Pretraining to Post-Training","created":"2026-07-17","cited_by_count":5,"area":"lr"},{"id":"2601.04537","title":"Linear Dynamics in the RLVR Training of Large Language Models","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2601.15609","title":"When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards","created":"2026-01-22","cited_by_count":4,"area":null},{"id":"2602.03978","title":"Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2602.15829","title":"Operationalising the Superficial Alignment Hypothesis via Task Complexity","created":"2026-02-17","cited_by_count":4,"area":null},{"id":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","cited_by_count":4,"area":"lr"},{"id":"2605.28142","title":"Self-Consistency via Marginal Sharpening","created":"2026-05-27","cited_by_count":4,"area":"lr"},{"id":"2606.27359","title":"When are likely answers right? On Sequence Probability and Correctness in LLMs","created":"2026-06-25","cited_by_count":4,"area":null},{"id":"2512.10309","title":"Tracking large chemical reaction networks and rare events by neural networks","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2601.18832","title":"The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning","created":"2026-01-25","cited_by_count":3,"area":"lr"},{"id":"2602.09276","title":"Effective Reasoning Chains Reduce Intrinsic Dimensionality","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2603.01301","title":"When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains","created":"2026-03-01","cited_by_count":3,"area":"lr"},{"id":"2603.06957","title":"Post-Training with Policy Gradients: Optimality and the Base Model Barrier","created":"2026-03-07","cited_by_count":3,"area":"deeprl"},{"id":"2603.07887","title":"Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2605.00742","title":"Position: agentic AI orchestration should be Bayes-consistent","created":"2026-05-01","cited_by_count":3,"area":"agents"},{"id":"2605.06241","title":"Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2605.09537","title":"Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning","created":"2026-05-10","cited_by_count":3,"area":"vla"},{"id":"2606.10587","title":"Towards Diverse Scientific Hypothesis Search with Large Language Models","created":"2026-06-09","cited_by_count":3,"area":null},{"id":"2510.18814","title":"A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning","created":"2025-10-21","cited_by_count":2,"area":"lr"},{"id":"2601.12269","title":"Simulated Annealing Enhances Theory-of-Mind Reasoning in Autoregressive Language Models","created":"2026-01-18","cited_by_count":2,"area":"lr"},{"id":"2602.18292","title":"Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers","created":"2026-02-20","cited_by_count":2,"area":null},{"id":"2603.03872","title":"Believe Your Model: Distribution-Guided Confidence Calibration","created":"2026-03-04","cited_by_count":2,"area":"lr"},{"id":"2603.18363","title":"PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2605.08817","title":"How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.11128","title":"Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2606.08543","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR","created":"2026-06-07","cited_by_count":2,"area":"lr"},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.29971","title":"NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2607.08940","title":"TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2512.06533","title":"Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning","created":"2025-12-06","cited_by_count":1,"area":"deeprl"},{"id":"2601.10267","title":"In-Context Source and Channel Coding","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2601.13566","title":"Self-Improvement as Coherence Optimization: A Theoretical Account","created":"2026-01-20","cited_by_count":1,"area":"synth"},{"id":"2601.14456","title":"On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2602.00238","title":"DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking","created":"2026-01-30","cited_by_count":1,"area":"rag"},{"id":"2602.01603","title":"Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2604.26326","title":"Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control","created":"2026-04-29","cited_by_count":1,"area":"lr"},{"id":"2605.11813","title":"Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.04272","title":"RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.09926","title":"Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling","created":"2026-06-07","cited_by_count":1,"area":"lr"},{"id":"2606.31484","title":"Fork-Think with Confidence","created":"2026-06-30","cited_by_count":1,"area":"lr"},{"id":"2607.06720","title":"When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning","created":"2026-07-07","cited_by_count":1,"area":"lr"},{"id":"2607.09693","title":"Depth-Entropy Guided Sampling for Training-Free LLM Reasoning","created":"2026-06-19","cited_by_count":1,"area":"lr"},{"id":"2608.14420","title":"More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2608.26120","title":"Recipes for Steering and Scaling LLMs via Sampling","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2609.35748","title":"Improving Test-Time Scaling with Adaptive Looped Transformers","created":"2026-09-28","cited_by_count":1,"area":"lr"},{"id":"2512.20169","title":"Learning to Reason in LLMs by Expectation Maximization","created":"2025-12-23","cited_by_count":0,"area":"lr"},{"id":"2602.00770","title":"Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models","created":"2026-01-31","cited_by_count":0,"area":"lr"},{"id":"2604.04855","title":"The Role of Generator Access in Autoregressive Post-Training","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.15672","title":"Faster LLM Inference via Sequential Monte Carlo","created":"2026-04-17","cited_by_count":0,"area":"inference"},{"id":"2604.16259","title":"Beyond Distribution Sharpening: The Importance of Task Rewards","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.06116","title":"Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.20189","title":"SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation","created":"2026-03-23","cited_by_count":0,"area":"agents"},{"id":"2605.28020","title":"The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2605.31126","title":"Not All Synthetic Data Is Yours to Learn From","created":"2026-05-29","cited_by_count":0,"area":"alignment"},{"id":"2607.01490","title":"Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2607.23854","title":"Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.00019","title":"Uncertainty-Aware Simulation-Based Inference for Operations Research with Large Language Models","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.30689","title":"CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.12243","title":"Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding","created":"2026-09-10","cited_by_count":0,"area":"lr"},{"id":"2609.12317","title":"Sampling via Decision-Flow: Training-Free Extraction of Improved Latent Reasoning Paths in Large Language Models","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.30352","title":"Strategic Self-Consistency","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2609.34181","title":"Efficient Reasoning via Constrained Optimization in Latent Space","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34905","title":"ReSight-SMC: Two-Stage Power Sampling via Island SMC with Visual Scouts","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34992","title":"Composable Decoding on the Probability Simplex: Theory and Implementation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37041","title":"Beam Search as Test-Time Self-Distillation via Counterfactual Contexts","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.38104","title":"Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.02140","title":"Finetuning with Sampling: SFT Learns Better Than You Think","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.05817","title":"Nash Equilibrium Text: A Game-Theoretic Decoding Framework for Text Generation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.13653","title":"A Critical Look at Power Sampling when Test Time Sharpening LLMs","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.20483","title":"Decoupled Marginal Sharpening for Training-Free Inference-Time Scaling","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}