{"total":89,"rows":[{"id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","created":"2025-09-29","cited_by_count":284,"area":"lr"},{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2503.07572","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning","created":"2025-03-10","cited_by_count":123,"area":"lr"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97,"area":"alignment"},{"id":"2505.15201","title":"Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems","created":"2025-05-21","cited_by_count":87,"area":"deeprl"},{"id":"2502.12118","title":"Scaling Test-Time Compute Without Verification or RL is Suboptimal","created":"2025-02-17","cited_by_count":84,"area":"lr"},{"id":"2506.02355","title":"Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening","created":"2025-06-03","cited_by_count":80,"area":"lr"},{"id":"2509.08755","title":"AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning","created":"2025-09-10","cited_by_count":72,"area":"agents"},{"id":"2503.14286","title":"Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs","created":"2025-03-18","cited_by_count":61,"area":null},{"id":"2502.13965","title":"Autellix: An Efficient Serving Engine for LLM Agents as General Programs","created":"2025-02-19","cited_by_count":58,"area":"agents"},{"id":"2503.19595","title":"Optimizing Language Models for Inference Time Objectives using Reinforcement Learning","created":"2025-03-25","cited_by_count":53,"area":null},{"id":"2502.06781","title":"Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning","created":"2025-02-10","cited_by_count":52,"area":"lr"},{"id":"2502.01839","title":"Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification","created":"2025-02-03","cited_by_count":50,"area":"lr"},{"id":"2601.18779","title":"POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration","created":"2026-01-26","cited_by_count":42,"area":"lr"},{"id":"2504.10478","title":"Weight Ensembling Improves Reasoning in Language Models","created":"2025-04-14","cited_by_count":38,"area":"lr"},{"id":"2507.14172","title":"Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI","created":"2025-07-10","cited_by_count":36,"area":"synth"},{"id":"2412.19792","title":"InfAlign: Inference-aware language model alignment","created":"2024-12-27","cited_by_count":35,"area":"alignment"},{"id":"2506.07976","title":"Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction","created":"2025-06-09","cited_by_count":34,"area":"lr"},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2601.21590","title":"Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening","created":"2026-01-29","cited_by_count":31,"area":"lr"},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2506.08379","title":"Reinforce LLM Reasoning through Multi-Agent Reflection","created":"2025-06-10","cited_by_count":27,"area":"lr"},{"id":"2504.07532","title":"AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation","created":"2025-04-10","cited_by_count":25,"area":"alignment"},{"id":"2504.15777","title":"Tina: Tiny Reasoning Models via LoRA","created":"2025-04-22","cited_by_count":25,"area":"lr"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2511.06411","title":"SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization","created":"2025-11-09","cited_by_count":21,"area":"lr"},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2510.23393","title":"The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation","created":"2025-10-27","cited_by_count":16,"area":null},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2512.02304","title":"When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers","created":"2025-12-02","cited_by_count":15,"area":null},{"id":"2509.24261","title":"Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models","created":"2025-09-29","cited_by_count":14,"area":"lr"},{"id":"2503.22456","title":"Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning","created":"2025-03-28","cited_by_count":13,"area":null},{"id":"2502.06217","title":"Examining False Positives under Inference Scaling for Mathematical Reasoning","created":"2025-02-10","cited_by_count":11,"area":"lr"},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"id":"2510.03669","title":"Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning","created":"2025-10-04","cited_by_count":10,"area":"lr"},{"id":"2510.26122","title":"Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking","created":"2025-10-30","cited_by_count":10,"area":"lr"},{"id":"2606.26091","title":"On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity","created":"2026-06-24","cited_by_count":10,"area":"distill"},{"id":"2505.18149","title":"First Finish Search: Efficient Test-Time Scaling in Large Language Models","created":"2025-05-23","cited_by_count":9,"area":"lr"},{"id":"2506.04611","title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","created":"2025-06-05","cited_by_count":9,"area":"lr"},{"id":"2602.21189","title":"Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2509.01649","title":"Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling","created":"2025-09-01","cited_by_count":7,"area":"lr"},{"id":"2509.25424","title":"Polychromic Objectives for Reinforcement Learning","created":"2025-09-29","cited_by_count":7,"area":"deeprl"},{"id":"2510.03971","title":"What Can You Do When You Have Zero Rewards During RL?","created":"2025-10-04","cited_by_count":7,"area":"lr"},{"id":"2505.14116","title":"Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst","created":"2025-05-20","cited_by_count":6,"area":"lr"},{"id":"2507.07981","title":"Why is Your Language Model a Poor Implicit Reward Model?","created":"2025-07-10","cited_by_count":6,"area":"alignment"},{"id":"2510.05077","title":"Slm-mux: Orchestrating small language models for reasoning","created":"2025-10-06","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":"2505.11730","title":"Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling","created":"2025-05-16","cited_by_count":5,"area":"lr"},{"id":"2510.03777","title":"GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time","created":"2025-10-04","cited_by_count":5,"area":null},{"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":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","cited_by_count":4,"area":"alignment"},{"id":"2604.19730","title":"FASTER: Value-Guided Sampling for Fast RL","created":"2026-04-21","cited_by_count":4,"area":"lr"},{"id":"2606.31511","title":"Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2607.27372","title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2603.14382","title":"StAR: Segment Anything Reasoner","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2604.10392","title":"Intent-aligned Formal Specification Synthesis via Traceable Refinement","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2605.15513","title":"CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning","created":"2026-05-15","cited_by_count":2,"area":"lr"},{"id":"2606.03962","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2607.14962","title":"Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation","created":"2026-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2608.17163","title":"Q-Learning With World Models","created":"2026-08-17","cited_by_count":2,"area":"wm"},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2603.22404","title":"Computational Arbitrage in AI Model Markets","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2506.21560","title":"Reinforcement learning fine-tuning of language model for instruction following and math reasoning","created":"2025-06-11","cited_by_count":0,"area":"lr"},{"id":"2601.22345","title":"Failing to Explore: Language Models on Interactive Tasks","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2605.06785","title":"Distributional Process Reward Models: Calibrated Prediction of Future Rewards via Conditional Optimal Transport","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.09853","title":"Exploration-Driven Optimization for Test-Time Large Language Model Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.10716","title":"What should post-training optimize? A test-time scaling law perspective","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2606.08231","title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","created":"2026-06-06","cited_by_count":0,"area":"lr"},{"id":"2606.17024","title":"ExpRL: Exploratory RL for LLM Mid-Training","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2606.18910","title":"REVES: REvision and VErification--Augmented Training for Test-Time Scaling","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"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":"2607.05392","title":"SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.17823","title":"Theoretical Foundations of $\\max$@$k$ Reinforcement Learning","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2607.23771","title":"Training Language Models to Cooperate with Inference-Time Controllers","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.14665","title":"When Does the Best Sampling Temperature Rise with the Budget? Sufficient Conditions for Pass@k","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.01274","title":"From Base Rollouts to RL Reasoning: A Budgeted Search Perspective","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.05842","title":"Do Quantum AIs Dream in Paths? Path-Integral Slow Thinking through Grover Interference","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.08082","title":"Inference-Time Nash Alignment","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2609.25575","title":"Direct Optimization of Generators for Search in Automated Theorem Proving","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.30352","title":"Strategic Self-Consistency","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"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":"2609.35793","title":"Learning from the Gap Between Pass@K and Pass@1","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.17735","title":"Train for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}