{"total":139,"rows":[{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"area":null},{"id":"2402.16906","title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","created":"2024-02-25","cited_by_count":127,"area":null},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2401.04621","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","created":"2024-01-09","cited_by_count":76,"area":null},{"id":"2404.10952","title":"Can Language Models Solve Olympiad Programming?","created":"2024-04-16","cited_by_count":72,"area":null},{"id":"2403.11322","title":"StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows","created":"2024-03-17","cited_by_count":65,"area":null},{"id":"2411.01679","title":"Autoformulation of Mathematical Optimization Models Using LLMs","created":"2024-11-03","cited_by_count":48,"area":null},{"id":"2402.10890","title":"When is Tree Search Useful for LLM Planning? It Depends on the Discriminator","created":"2024-02-16","cited_by_count":47,"area":null},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46,"area":null},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2402.04315","title":"Training Language Models to Generate Text with Citations via Fine-grained Rewards","created":"2024-02-06","cited_by_count":42,"area":null},{"id":"2311.08588","title":"CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation","created":"2023-11-14","cited_by_count":39,"area":null},{"id":"2412.10999","title":"Cocoa: Co-Planning and Co-Execution with AI Agents","created":"2024-12-14","cited_by_count":39,"area":null},{"id":"2502.13681","title":"Repo2Run: Automated Building Executable Environment for Code Repository at Scale","created":"2025-02-19","cited_by_count":39,"area":null},{"id":"2407.14414","title":"System-1.x: Learning to Balance Fast and Slow Planning with Language Models","created":"2024-07-19","cited_by_count":35,"area":null},{"id":"2312.07413","title":"AI capabilities can be significantly improved without expensive retraining","created":"2023-12-12","cited_by_count":28,"area":null},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"area":null},{"id":"2311.09830","title":"Automating the Generation of Prompts for LLM-based Action Choice in PDDL Planning","created":"2023-11-16","cited_by_count":24,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2312.14950","title":"TypeFly: Flying Drones with Large Language Model","created":"2023-12-08","cited_by_count":23,"area":null},{"id":"2504.16082","title":"MR. Video: \"MapReduce\" is the Principle for Long Video Understanding","created":"2025-04-22","cited_by_count":23,"area":null},{"id":"2606.11926","title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","created":"2026-06-10","cited_by_count":22,"area":null},{"id":"2401.06437","title":"3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?","created":"2024-01-12","cited_by_count":21,"area":null},{"id":"2504.10445","title":"RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users","created":"2025-04-14","cited_by_count":21,"area":null},{"id":"2602.11757","title":"Code2Worlds: Empowering Coding LLMs for 4D World Generation","created":"2026-02-12","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":"2505.11122","title":"Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Factor Mining","created":"2025-05-16","cited_by_count":16,"area":null},{"id":"2401.08664","title":"Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges","created":"2023-12-27","cited_by_count":13,"area":null},{"id":"2410.15580","title":"Language Models are Symbolic Learners in Arithmetic","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2505.18098","title":"Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2411.01414","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2605.13625","title":"How to Interpret Agent Behavior","created":"2026-05-13","cited_by_count":10,"area":null},{"id":"2502.16706","title":"DISC: Dynamic Decomposition Improves LLM Inference Scaling","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2511.05931","title":"Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement","created":"2025-11-08","cited_by_count":9,"area":null},{"id":"2604.27043","title":"CL-bench Life: Can Language Models Learn from Real-Life Context?","created":"2026-04-29","cited_by_count":9,"area":null},{"id":"2406.13161","title":"APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts","created":"2024-06-19","cited_by_count":8,"area":null},{"id":"2502.00225","title":"Should You Use Your Large Language Model to Explore or Exploit?","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2401.07870","title":"JumpCoder: Go Beyond Autoregressive Coder via Online Modification","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2405.01453","title":"Creative Problem Solving in Large Language and Vision Models -- What Would it Take?","created":"2024-05-02","cited_by_count":7,"area":null},{"id":"2406.15275","title":"How language models extrapolate outside the training data: A case study in Textualized Gridworld","created":"2024-06-21","cited_by_count":7,"area":null},{"id":"2407.10735","title":"Transforming Agency. On the mode of existence of Large Language Models","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2506.06376","title":"Enhancing Decision-Making of Large Language Models via Actor-Critic","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2510.00510","title":"JoyAgent-JDGenie: Technical Report on the GAIA","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2603.05863","title":"ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2401.05940","title":"Mutation-based Consistency Testing for Evaluating the Code Understanding Capability of LLMs","created":"2024-01-11","cited_by_count":6,"area":null},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2601.03764","title":"Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model","created":"2026-01-07","cited_by_count":6,"area":null},{"id":"2408.11198","title":"Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2505.14656","title":"Cost-Awareness in Tree-Search LLM Planning: A Systematic Study","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2402.08756","title":"Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2411.08254","title":"Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropy","created":"2024-11-13","cited_by_count":4,"area":null},{"id":"2503.19007","title":"Option Discovery Using LLM-guided Semantic Hierarchical Reinforcement Learning","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2504.07433","title":"From Token to Line: Enhancing Code Generation with a Long-Term Perspective","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2505.19768","title":"T^2Agent A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2605.09730","title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","created":"2026-05-10","cited_by_count":4,"area":null},{"id":"2409.04114","title":"Multi-Programming Language Ensemble for Code Generation in Large Language Model","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2409.19382","title":"Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models","created":"2024-09-28","cited_by_count":3,"area":null},{"id":"2411.15758","title":"Decoding Urban Industrial Complexity: Enhancing Knowledge-Driven Insights via IndustryScopeGPT","created":"2024-11-24","cited_by_count":3,"area":null},{"id":"2412.06229","title":"LLMs as Debate Partners: Utilizing Genetic Algorithms and Adversarial Search for Adaptive Arguments","created":"2024-12-09","cited_by_count":3,"area":null},{"id":"2501.19318","title":"MINDSTORES: Memory-Informed Neural Decision Synthesis for Task-Oriented Reinforcement in Embodied Systems","created":"2025-01-31","cited_by_count":3,"area":null},{"id":"2508.07571","title":"Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression","created":"2025-08-11","cited_by_count":3,"area":null},{"id":"2512.00672","title":"ML-Tool-Bench: Tool-Augmented Planning for ML Tasks","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2601.04789","title":"NC2C: Automated Convexification of Generic Non-Convex Optimization Problems","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2603.20366","title":"WebNavigator: Global Web Navigation via Interaction Graph Retrieval","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2604.12126","title":"Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2605.18636","title":"SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2408.16667","title":"Iterative Graph Alignment","created":"2024-08-29","cited_by_count":2,"area":null},{"id":"2502.12669","title":"Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2503.11586","title":"Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2505.10861","title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.07557","title":"SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2509.18607","title":"Reflect before Act: Proactive Error Correction in Language Models","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2601.04219","title":"AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2602.07839","title":"TodoEvolve: Learning to Architect Agent Planning Systems","created":"2026-02-08","cited_by_count":2,"area":null},{"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":"2603.24780","title":"Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2605.21516","title":"Harnesses for Inference-Time Alignment over Execution Trajectories","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.29682","title":"Scaling Laws for Agent Harnesses via Effective Feedback Compute","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.03726","title":"SelfMem: Self-Optimizing Memory for AI Agents","created":"2026-07-04","cited_by_count":2,"area":null},{"id":"2608.26701","title":"Accelerating Scientific Research with Gemini in the Real-World","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2407.19055","title":"Effective Large Language Model Debugging with Best-first Tree Search","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2408.08463","title":"A theory of understanding for artificial intelligence: composability, catalysts, and learning","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2504.01248","title":"Automated Factual Benchmarking for In-Car Conversational Systems using Large Language Models","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2511.09900","title":"Boosting In-Silicon Directed Evolution with Fine-Tuned Protein Language Model and Tree Search","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2512.01853","title":"COACH: Collaborative Agents for Contextual Highlighting -- A Multi-Agent Framework for Sports Video Analysis","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2512.25065","title":"Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.22662","title":"Task-Aware LLM Council with Adaptive Decision Pathways for Decision Support","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.14712","title":"SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2604.21354","title":"Decoupled Travel Planning with Behavior Forest","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.12755","title":"State-Centric Decision Process","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2607.07779","title":"From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.01604","title":"Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.03738","title":"AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuits","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2609.05446","title":"AutoFyn Technical Report: Non-Parametric Expert Iteration for Long-Horizon Agents","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2609.37923","title":"EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2610.01834","title":"Code Owns the Simulation, Jev Owns the Evaluation","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2610.08077","title":"Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight","created":"2026-10-06","cited_by_count":1,"area":null}],"next_cursor":"100"}