{"total":135,"rows":[{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250,"area":"lr"},{"id":"2506.15841","title":"MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents","created":"2025-06-18","cited_by_count":238,"area":"lr"},{"id":"2505.00949","title":"Llama-Nemotron: Efficient Reasoning Models","created":"2025-05-02","cited_by_count":158,"area":"lr"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2505.15778","title":"Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space","created":"2025-05-21","cited_by_count":117,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2405.09783","title":"LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery","created":"2024-05-16","cited_by_count":86,"area":"lr"},{"id":"2502.10325","title":"Process Reward Models for LLM Agents: Practical Framework and Directions","created":"2025-02-14","cited_by_count":85,"area":"lr"},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2502.12215","title":"Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?","created":"2025-02-17","cited_by_count":70,"area":"lr"},{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63,"area":"lr"},{"id":"2511.20785","title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","created":"2025-11-25","cited_by_count":61,"area":"lr"},{"id":"2509.02208","title":"Baichuan-M2: Scaling Medical Capability with Large Verifier System","created":"2025-09-02","cited_by_count":59,"area":"lr"},{"id":"2412.20993","title":"Efficiently Scaling LLM Reasoning with Certaindex","created":"2024-12-30","cited_by_count":58,"area":"lr"},{"id":"2603.05433","title":"CRISP: Compressed Reasoning via Iterative Self-Policy Distillation","created":"2026-03-05","cited_by_count":58,"area":"lr"},{"id":"2510.18855","title":"Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model","created":"2025-10-21","cited_by_count":55,"area":"lr"},{"id":"2503.06692","title":"InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models","created":"2025-03-09","cited_by_count":54,"area":"lr"},{"id":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","cited_by_count":43,"area":"lr"},{"id":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2508.18588","title":"History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL","created":"2025-08-26","cited_by_count":38,"area":"lr"},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25,"area":"lr"},{"id":"2510.13744","title":"Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math","created":"2025-10-15","cited_by_count":22,"area":"lr"},{"id":"2505.15801","title":"VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models","created":"2025-05-21","cited_by_count":20,"area":"lr"},{"id":"2510.26475","title":"ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems","created":"2025-10-30","cited_by_count":18,"area":"lr"},{"id":"2604.09852","title":"MEMENTO: Teaching LLMs to Manage Their Own Context","created":"2026-04-10","cited_by_count":18,"area":"lr"},{"id":"2506.01369","title":"Incentivizing LLMs to Self-Verify Their Answers","created":"2025-06-02","cited_by_count":17,"area":"lr"},{"id":"2511.10645","title":"ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference","created":"2025-11-13","cited_by_count":17,"area":"lr"},{"id":"2511.08577","title":"Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning","created":"2025-11-11","cited_by_count":16,"area":"lr"},{"id":"2602.08847","title":"Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems","created":"2026-02-09","cited_by_count":16,"area":"lr"},{"id":"2405.17438","title":"An LLM-Tool Compiler for Fused Parallel Function Calling","created":"2024-05-07","cited_by_count":15,"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":"2505.14733","title":"The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute","created":"2025-05-20","cited_by_count":15,"area":"lr"},{"id":"2505.04842","title":"Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers","created":"2025-05-07","cited_by_count":14,"area":"lr"},{"id":"2505.17155","title":"TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling","created":"2025-05-22","cited_by_count":14,"area":"lr"},{"id":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"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":"2602.03048","title":"CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2603.04304","title":"$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners","created":"2026-03-04","cited_by_count":12,"area":"lr"},{"id":"2510.19225","title":"RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs","created":"2025-10-22","cited_by_count":11,"area":"lr"},{"id":"2510.19669","title":"DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference","created":"2025-10-22","cited_by_count":11,"area":"lr"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","cited_by_count":11,"area":"lr"},{"id":"2506.22950","title":"Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models","created":"2025-06-28","cited_by_count":10,"area":"lr"},{"id":"2508.15746","title":"End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning","created":"2025-08-21","cited_by_count":10,"area":"lr"},{"id":"2510.08525","title":"Which Heads Matter for Reasoning? RL-Guided KV Cache Compression","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2512.01278","title":"Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding","created":"2025-12-01","cited_by_count":10,"area":"lr"},{"id":"2605.07177","title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","created":"2026-05-08","cited_by_count":10,"area":"lr"},{"id":"2505.14412","title":"PRL: Prompts from Reinforcement Learning","created":"2025-05-20","cited_by_count":9,"area":"lr"},{"id":"2512.15176","title":"DEER: Draft with Diffusion, Verify with Autoregressive Models","created":"2025-12-17","cited_by_count":9,"area":"lr"},{"id":"2604.14267","title":"Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization","created":"2026-04-15","cited_by_count":9,"area":"lr"},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"id":"2511.13612","title":"P1: Mastering Physics Olympiads with Reinforcement Learning","created":"2025-11-17","cited_by_count":8,"area":"lr"},{"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":"2602.13953","title":"QuRL: Efficient Reinforcement Learning with Quantized Rollout","created":"2026-02-15","cited_by_count":8,"area":"lr"},{"id":"2406.11823","title":"On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2503.09620","title":"Exploiting Edited Large Language Models as General Scientific Optimizers","created":"2025-03-08","cited_by_count":7,"area":"lr"},{"id":"2509.24869","title":"Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2512.10931","title":"Asynchronous Reasoning: Training-Free Interactive Thinking LLMs","created":"2025-12-11","cited_by_count":7,"area":"lr"},{"id":"2604.11554","title":"Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale","created":"2026-04-13","cited_by_count":7,"area":"lr"},{"id":"2609.11042","title":"T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks","created":"2026-09-10","cited_by_count":7,"area":"lr"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2510.09133","title":"On the Provable Performance Guarantee of Efficient Reasoning Models","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2511.14366","title":"ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning","created":"2025-11-18","cited_by_count":6,"area":"lr"},{"id":"2512.02874","title":"Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning","created":"2025-12-02","cited_by_count":6,"area":"lr"},{"id":"2602.01469","title":"P-EAGLE: Parallel-Drafting EAGLE with Scalable Training","created":"2026-02-01","cited_by_count":6,"area":"lr"},{"id":"2603.17998","title":"The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering","created":"2026-03-18","cited_by_count":6,"area":"lr"},{"id":"2603.23414","title":"SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling","created":"2026-03-24","cited_by_count":6,"area":"lr"},{"id":"2606.09348","title":"PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment","created":"2026-06-08","cited_by_count":6,"area":"lr"},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2608.14277","title":"SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning","created":"2026-08-14","cited_by_count":6,"area":"lr"},{"id":"2503.13661","title":"Pensez: Less Data, Better Reasoning -- Rethinking French LLM","created":"2025-03-17","cited_by_count":5,"area":"lr"},{"id":"2504.20157","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2505.14147","title":"SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning","created":"2025-05-20","cited_by_count":5,"area":"lr"},{"id":"2601.09083","title":"SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache","created":"2026-01-14","cited_by_count":5,"area":"lr"},{"id":"2502.15132","title":"CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations","created":"2025-02-21","cited_by_count":4,"area":"lr"},{"id":"2512.01925","title":"Rectifying LLM Thought from Lens of Optimization","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2602.01698","title":"Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2605.12495","title":"AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward","created":"2026-05-12","cited_by_count":4,"area":"lr"},{"id":"2606.26997","title":"RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning","created":"2026-06-25","cited_by_count":4,"area":"lr"},{"id":"2509.00195","title":"FastTTS: Accelerating Test-Time Scaling for Edge LLM Reasoning","created":"2025-08-29","cited_by_count":3,"area":"lr"},{"id":"2509.15148","title":"ATTS: Asynchronous Test-Time Scaling via Conformal Prediction","created":"2025-09-18","cited_by_count":3,"area":"lr"},{"id":"2510.16276","title":"What Limits Agentic Systems Efficiency?","created":"2025-10-18","cited_by_count":3,"area":"lr"},{"id":"2602.01103","title":"Probing RLVR training instability through the lens of objective-level hacking","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2602.08167","title":"Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2603.06619","title":"Not all tokens are needed(NAT): token efficient reinforcement learning","created":"2026-02-20","cited_by_count":3,"area":"lr"},{"id":"2605.22566","title":"GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2608.09682","title":"Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning","created":"2026-08-10","cited_by_count":3,"area":"lr"},{"id":"2508.18736","title":"Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2510.14620","title":"Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models","created":"2025-10-16","cited_by_count":2,"area":"lr"},{"id":"2601.03969","title":"Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models","created":"2026-01-07","cited_by_count":2,"area":"lr"},{"id":"2601.08274","title":"Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2605.02162","title":"AAFLOW: Scalable Patterns for Agentic AI Workflows","created":"2026-05-04","cited_by_count":2,"area":"lr"},{"id":"2605.06850","title":"How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.28184","title":"Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.01215","title":"Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs","created":"2026-05-31","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}