{"total":83,"rows":[{"id":"2503.18892","title":"SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild","created":"2025-03-24","cited_by_count":511,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2411.06559","title":"Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents","created":"2024-11-10","cited_by_count":154,"area":"wm"},{"id":"2411.00820","title":"AutoGLM: Autonomous Foundation Agents for GUIs","created":"2024-10-28","cited_by_count":100,"area":"agents"},{"id":"2410.18927","title":"SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models","created":"2024-10-24","cited_by_count":69,"area":"safety"},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2411.15692","title":"DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration","created":"2024-11-24","cited_by_count":44,"area":"agents"},{"id":"2506.11425","title":"Agent-RLVR: Training Software Engineering Agents via Guidance and Environment Rewards","created":"2025-06-13","cited_by_count":42,"area":"lr"},{"id":"2503.18971","title":"LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models","created":"2025-03-22","cited_by_count":38,"area":null},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2502.05234","title":"Optimizing Temperature for Language Models with Multi-Sample Inference","created":"2025-02-07","cited_by_count":33,"area":"lr"},{"id":"2503.07832","title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","created":"2025-03-10","cited_by_count":30,"area":"lr"},{"id":"2409.09584","title":"RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation","created":"2024-09-15","cited_by_count":26,"area":"lr"},{"id":"2412.17256","title":"B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners","created":"2024-12-23","cited_by_count":26,"area":"lr"},{"id":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25,"area":"agents"},{"id":"2501.10069","title":"A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworks","created":"2025-01-17","cited_by_count":21,"area":"lr"},{"id":"2604.19341","title":"Structured Scaling of AI Discovery Across Diverse Scientific Domains","created":"2026-04-21","cited_by_count":21,"area":null},{"id":"2505.00234","title":"Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks","created":"2025-05-01","cited_by_count":19,"area":"agents"},{"id":"2509.16198","title":"RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation","created":"2025-09-19","cited_by_count":19,"area":null},{"id":"2502.11027","title":"On the Effect of Sampling Diversity in Scaling LLM Inference","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2504.14047","title":"Rethinking Inference-Time Scaling: Efficiency Limits and Linguistic Signals","created":"2025-04-18","cited_by_count":18,"area":"lr"},{"id":"2502.14634","title":"CER: Confidence Enhanced Reasoning in LLMs","created":"2025-02-20","cited_by_count":17,"area":"lr"},{"id":"2503.17502","title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","created":"2025-03-21","cited_by_count":16,"area":null},{"id":"2502.16111","title":"PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving","created":"2025-02-22","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":"2509.13351","title":"Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning","created":"2025-09-14","cited_by_count":15,"area":"lr"},{"id":"2507.08944","title":"Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents","created":"2025-07-11","cited_by_count":14,"area":"agents"},{"id":"2411.05010","title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","created":"2024-10-22","cited_by_count":10,"area":"lr"},{"id":"2411.11053","title":"SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation","created":"2024-11-17","cited_by_count":10,"area":"lr"},{"id":"2509.16456","title":"GPO: Learning from Critical Steps to Improve LLM Reasoning","created":"2025-09-19","cited_by_count":10,"area":"lr"},{"id":"2502.16706","title":"DISC: Dynamic Decomposition Improves LLM Inference Scaling","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2505.17652","title":"Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective","created":"2025-05-23","cited_by_count":9,"area":"lr"},{"id":"2505.20881","title":"Generalizable Heuristic Generation Through LLMs with Meta-Optimization","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2510.14321","title":"Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2505.18384","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2510.00510","title":"JoyAgent-JDGenie: Technical Report on the GAIA","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2412.13422","title":"Generating Diverse Hypotheses for Inductive Reasoning","created":"2024-12-18","cited_by_count":6,"area":"lr"},{"id":"2511.01912","title":"EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory","created":"2025-11-01","cited_by_count":6,"area":"agents"},{"id":"2504.01281","title":"Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding","created":"2025-04-02","cited_by_count":5,"area":"rag"},{"id":"2505.18071","title":"Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"id":"2411.07595","title":"Entropy Controllable Direct Preference Optimization","created":"2024-11-12","cited_by_count":4,"area":"alignment"},{"id":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2505.15356","title":"NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2509.17393","title":"Program Synthesis via Test-Time Transduction","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2510.03851","title":"MetaMuse: Algorithm Generation via Creative Ideation","created":"2025-10-04","cited_by_count":4,"area":null},{"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":"2412.12544","title":"Seed-CTS: Unleashing the Power of Tree Search for Superior Performance in Competitive Coding Tasks","created":"2024-12-17","cited_by_count":3,"area":"lr"},{"id":"2505.18557","title":"TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2603.02787","title":"Rethinking Code Similarity for Automated Algorithm Design with LLMs","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2603.20256","title":"SciNav: A General Agent Framework for Scientific Coding Tasks","created":"2026-03-11","cited_by_count":3,"area":"agents"},{"id":"2505.12500","title":"MARGE: Improving Math Reasoning for LLMs with Guided Exploration","created":"2025-05-18","cited_by_count":2,"area":"lr"},{"id":"2508.13156","title":"EvoVerilog: Large Langugage Model Assisted Evolution of Verilog Code","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2509.23595","title":"Timber: Training-free Instruct Model Refining with Base via Effective Rank","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2509.25420","title":"Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search","created":"2025-09-29","cited_by_count":2,"area":"lr"},{"id":"2602.00299","title":"Agentic Framework for Epidemiological Modeling","created":"2026-01-30","cited_by_count":2,"area":"agents"},{"id":"2602.02103","title":"How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2602.14083","title":"Plan-MCTS: Plan Exploration for Action Exploitation in Web Navigation","created":"2026-02-15","cited_by_count":2,"area":null},{"id":"2605.08670","title":"MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction","created":"2026-05-09","cited_by_count":2,"area":"agents"},{"id":"2606.16999","title":"Selection Without Signal, Recovery Through Expression: A Measurement Study of Post-Hoc Falsification Operators for Frozen Small Code Models","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2505.20182","title":"An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2507.10182","title":"Breaking the Myth: Can Small Models Infer Postconditions Too?","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2511.08043","title":"DynaAct: Large Language Model Reasoning with Dynamic Action Spaces","created":"2025-11-11","cited_by_count":1,"area":"lr"},{"id":"2511.19895","title":"RPM-MCTS: Knowledge-Retrieval as Process Reward Model with Monte Carlo Tree Search for Code Generation","created":"2025-11-25","cited_by_count":1,"area":"lr"},{"id":"2601.07293","title":"Inference-Time Scaling for Visual AutoRegressive modeling by Searching Representative Samples","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2605.02289","title":"EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2605.15607","title":"Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2608.08958","title":"Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods","created":"2026-08-09","cited_by_count":1,"area":"lr"},{"id":"2502.15872","title":"MutaGReP: Execution-Free Repository-Grounded Plan Search for Code-Use","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2507.15892","title":"StaAgent: An Agentic Framework for Testing Static Analyzers","created":"2025-07-20","cited_by_count":0,"area":"agents"},{"id":"2602.14054","title":"LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2604.23989","title":"Understanding Scattered Forest Search: A Version-Space Perspective on Multi-Turn Program Correction","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.00932","title":"Code World Model Preparedness Report","created":"2026-05-01","cited_by_count":0,"area":"wm"},{"id":"2605.11299","title":"Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2607.02390","title":"DecompRL: Solving Harder Problems by Learning Modular Code Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.30395","title":"When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.33155","title":"Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction?","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.39568","title":"Self-Spec Verifiable Code Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05322","title":"When Does Longer Reasoning Help? Predicting Mathematical Reasoning Through Discovery and Execution","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}