{"total":132,"rows":[{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285,"area":"agents"},{"id":"2504.03601","title":"APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay","created":"2025-04-04","cited_by_count":167,"area":"agents"},{"id":"2505.20411","title":"SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents","created":"2025-05-26","cited_by_count":142,"area":"agents"},{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124,"area":"agents"},{"id":"2506.18824","title":"Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories","created":"2025-06-23","cited_by_count":81,"area":"lr"},{"id":"2507.02554","title":"AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench","created":"2025-07-03","cited_by_count":71,"area":"agents"},{"id":"2508.02085","title":"SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents","created":"2025-08-04","cited_by_count":69,"area":"lr"},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2503.11733","title":"LLM Agents for Education: Advances and Applications","created":"2025-03-14","cited_by_count":59,"area":"agents"},{"id":"2503.04412","title":"Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search","created":"2025-03-06","cited_by_count":51,"area":"lr"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2508.21433","title":"The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management","created":"2025-08-29","cited_by_count":48,"area":"agents"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2508.03501","title":"Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":36,"area":"lr"},{"id":"2602.04837","title":"Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing","created":"2026-02-04","cited_by_count":36,"area":"synth"},{"id":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30,"area":null},{"id":"2509.02360","title":"When Agents go Astray: Course-Correcting SWE Agents with PRMs","created":"2025-09-02","cited_by_count":28,"area":"agents"},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27,"area":null},{"id":"2506.07636","title":"SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling","created":"2025-06-09","cited_by_count":26,"area":"agents"},{"id":"2505.20660","title":"BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism","created":"2025-05-27","cited_by_count":25,"area":"agents"},{"id":"2502.07942","title":"Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs","created":"2025-02-11","cited_by_count":24,"area":"agents"},{"id":"2411.10213","title":"An Empirical Study on LLM-based Agents for Automated Bug Fixing","created":"2024-11-15","cited_by_count":23,"area":"agents"},{"id":"2502.02747","title":"PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification","created":"2025-02-04","cited_by_count":22,"area":"agents"},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2603.03194","title":"BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?","created":"2026-03-03","cited_by_count":22,"area":"agents"},{"id":"2503.14269","title":"DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal","created":"2025-03-18","cited_by_count":20,"area":"agents"},{"id":"2505.11556","title":"Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs","created":"2025-05-15","cited_by_count":19,"area":"lr"},{"id":"2506.14683","title":"Unified Software Engineering Agent as AI Software Engineer","created":"2025-06-17","cited_by_count":19,"area":"agents"},{"id":"2509.09853","title":"SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints","created":"2025-09-11","cited_by_count":17,"area":"agents"},{"id":"2604.14820","title":"SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling","created":"2026-04-16","cited_by_count":16,"area":"lr"},{"id":"2503.01811","title":"AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2604.16529","title":"Scaling Test-Time Compute for Agentic Coding","created":"2026-04-16","cited_by_count":15,"area":"lr"},{"id":"2604.05477","title":"Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction","created":"2026-04-07","cited_by_count":14,"area":"agents"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2512.12216","title":"Training Versatile Coding Agents in Synthetic Environments","created":"2025-12-13","cited_by_count":13,"area":"agents"},{"id":"2505.18955","title":"Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models","created":"2025-05-25","cited_by_count":12,"area":"lr"},{"id":"2506.16136","title":"Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing","created":"2025-06-19","cited_by_count":12,"area":"lr"},{"id":"2601.22129","title":"SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents","created":"2026-01-29","cited_by_count":12,"area":"lr"},{"id":"2602.21611","title":"Structurally Aligned Subtask-Level Memory for Software Engineering Agents","created":"2026-02-25","cited_by_count":12,"area":"agents"},{"id":"2605.22781","title":"DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback","created":"2026-05-21","cited_by_count":12,"area":"agents"},{"id":"2505.13652","title":"Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents","created":"2025-05-19","cited_by_count":10,"area":"lr"},{"id":"2606.25447","title":"The Interplay of Harness Design and Post-Training in LLM Agents","created":"2026-06-24","cited_by_count":10,"area":"agents"},{"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":"2602.23647","title":"SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair","created":"2026-02-27","cited_by_count":9,"area":"agents"},{"id":"2603.20691","title":"SWE-Next: Scalable Real-World Software Engineering Tasks for Agents","created":"2026-03-21","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2504.08696","title":"SeaView: Software Engineering Agent Visual Interface for Enhanced Workflow","created":"2025-04-11","cited_by_count":7,"area":"agents"},{"id":"2511.16004","title":"InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution","created":"2025-11-20","cited_by_count":7,"area":null},{"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":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2602.16819","title":"Hybrid-Gym: Training Coding Agents to Generalize Across Tasks","created":"2026-02-18","cited_by_count":6,"area":"agents"},{"id":"2603.01048","title":"RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair","created":"2026-03-01","cited_by_count":6,"area":null},{"id":"2604.11716","title":"SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context","created":"2026-04-13","cited_by_count":6,"area":null},{"id":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2602.11210","title":"SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents","created":"2026-02-11","cited_by_count":5,"area":"lr"},{"id":"2603.15707","title":"SEMAG: Self-Evolutionary Multi-Agent Code Generation","created":"2026-03-16","cited_by_count":5,"area":"agents"},{"id":"2604.10493","title":"SWE-Shepherd: Advancing PRMs for Reinforcing Code Agents","created":"2026-04-12","cited_by_count":5,"area":"agents"},{"id":"2605.11556","title":"Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers","created":"2026-05-12","cited_by_count":5,"area":"lr"},{"id":"2606.14066","title":"FastContext: Training Efficient Repository Explorer for Coding Agents","created":"2026-06-12","cited_by_count":5,"area":"agents"},{"id":"2608.03222","title":"Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks","created":"2026-08-04","cited_by_count":5,"area":"agents"},{"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":"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":"2603.01327","title":"SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution","created":"2026-03-01","cited_by_count":4,"area":"agents"},{"id":"2603.13258","title":"Your Code Agent Can Grow Alongside You with Structured Memory","created":"2026-02-25","cited_by_count":4,"area":"agents"},{"id":"2604.16790","title":"Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2608.14354","title":"ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond","created":"2026-08-14","cited_by_count":4,"area":"agents"},{"id":"2609.07925","title":"FrogNano: Training a 4B Coding Agent via Online Task Synthesis","created":"2026-09-07","cited_by_count":4,"area":"agents"},{"id":"2511.16005","title":"InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2601.23257","title":"From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2604.05481","title":"On the Role of Fault Localization Context for LLM-Based Program Repair","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2606.14061","title":"LLM Agents Can See Code Repositories","created":"2026-06-12","cited_by_count":3,"area":"agents"},{"id":"2606.20625","title":"AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents","created":"2026-05-26","cited_by_count":3,"area":"lr"},{"id":"2608.11386","title":"The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior","created":"2026-08-11","cited_by_count":3,"area":"agents"},{"id":"2601.05539","title":"LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis","created":"2026-01-09","cited_by_count":2,"area":"agents"},{"id":"2601.09883","title":"Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL","created":"2026-01-14","cited_by_count":2,"area":"agents"},{"id":"2601.13933","title":"VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution","created":"2026-01-20","cited_by_count":2,"area":"agents"},{"id":"2602.05242","title":"EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.06090","title":"SVRepair: Structured Visual Reasoning for Automated Program Repair","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2603.17826","title":"FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2603.26458","title":"Can AI Models Direct Each Other? Organizational Structure as a Probe into Training Limitations","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2606.25198","title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","created":"2026-06-23","cited_by_count":2,"area":"agents"},{"id":"2607.18859","title":"PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.03392","title":"Self-Evolving Coding Agents","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2608.18933","title":"SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution","created":"2026-08-19","cited_by_count":2,"area":"agents"},{"id":"2608.23848","title":"Exploit More, Explore Smarter for Budget-Constrained Agentic Search","created":"2026-08-24","cited_by_count":2,"area":"agents"},{"id":"2609.04075","title":"PatchBench: Evaluating AI Agents for Vulnerability Patching","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2509.11507","title":"MedicalOS: An LLM Agent based Operating System for Digital Healthcare","created":"2025-09-15","cited_by_count":1,"area":"agents"},{"id":"2510.19995","title":"Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication","created":"2025-10-22","cited_by_count":1,"area":"agents"},{"id":"2510.26287","title":"Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search","created":"2025-10-30","cited_by_count":1,"area":"agents"},{"id":"2511.03925","title":"Collaborative Agents for Automated Program Repair in Ruby","created":"2025-11-06","cited_by_count":1,"area":"agents"},{"id":"2512.01396","title":"BackportBench: A Multilingual Benchmark for Automated Backporting of Patches","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2602.07457","title":"Pull Requests as a Training Signal for Repo-Level Code Editing","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.07883","title":"ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation","created":"2026-02-08","cited_by_count":1,"area":"agents"},{"id":"2604.19750","title":"Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2605.18851","title":"STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2605.27954","title":"Cyclical Entropy Eruption: Entropy Dynamics in Agent Reinforcement Learning","created":"2026-05-27","cited_by_count":1,"area":"agents"},{"id":"2606.20512","title":"Probe-and-Refine Tuning of Repository Guidance for Coding Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}