{"total":85,"rows":[{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"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":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95,"area":"agents"},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"id":"2603.24755","title":"SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks","created":"2026-03-25","cited_by_count":30,"area":"agents"},{"id":"2602.23866","title":"SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale","created":"2026-02-27","cited_by_count":29,"area":"agents"},{"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":"2602.05892","title":"ContextBench: A Benchmark for Context Retrieval in Coding Agents","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2602.09892","title":"Immersion in the GitHub Universe: Scaling Coding Agents to Mastery","created":"2026-02-10","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":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2510.08996","title":"Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2603.22862","title":"The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration","created":"2026-03-24","cited_by_count":14,"area":"agents"},{"id":"2506.00750","title":"CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning","created":"2025-05-31","cited_by_count":13,"area":"lr"},{"id":"2507.21184","title":"Can Language Models Discover Scaling Laws?","created":"2025-07-27","cited_by_count":13,"area":null},{"id":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2511.05459","title":"SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models","created":"2025-11-07","cited_by_count":11,"area":"agents"},{"id":"2606.16038","title":"Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents","created":"2026-06-14","cited_by_count":10,"area":"agents"},{"id":"2602.22764","title":"Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents","created":"2026-02-26","cited_by_count":8,"area":"agents"},{"id":"2605.08693","title":"SkillMaster: Toward Autonomous Skill Mastery in LLM Agents","created":"2026-05-09","cited_by_count":8,"area":"agents"},{"id":"2606.22504","title":"Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents","created":"2026-06-21","cited_by_count":8,"area":"agents"},{"id":"2509.22237","title":"FeatBench: Towards More Realistic Evaluation of Feature-level Code Generation","created":"2025-09-26","cited_by_count":6,"area":null},{"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":"2605.14859","title":"Do Coding Agents Understand Least-Privilege Authorization?","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2608.09802","title":"SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring","created":"2026-08-10","cited_by_count":6,"area":"agents"},{"id":"2505.23932","title":"SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2507.10646","title":"CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2510.26852","title":"CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments","created":"2025-10-30","cited_by_count":5,"area":"agents"},{"id":"2512.20482","title":"SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2604.01527","title":"REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage","created":"2026-04-02","cited_by_count":5,"area":"agents"},{"id":"2607.00990","title":"SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests","created":"2026-07-01","cited_by_count":5,"area":"agents"},{"id":"2607.06184","title":"What Resolve Rate Hides: Trajectory Structure Diagnostics for Coding Agents","created":"2026-07-07","cited_by_count":5,"area":"agents"},{"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":"2602.02262","title":"OmniCode: A Benchmark for Evaluating Software Engineering Agents","created":"2026-02-02","cited_by_count":4,"area":"agents"},{"id":"2603.26137","title":"ATime-Consistent Benchmark for Repository-Level Software Engineering Evaluation","created":"2026-03-27","cited_by_count":3,"area":null},{"id":"2604.16321","title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2605.06445","title":"Constraint Decay: The Fragility of LLM Agents in Backend Code Generation","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2605.26177","title":"RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2606.30963","title":"Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2609.17930","title":"Locating Hidden Failures Makes Long-Horizon Agents More Reliable","created":"2026-09-15","cited_by_count":3,"area":null},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2605.27489","title":"HARP: Measuring Harm Amplification in Multi-Agent LLM Systems","created":"2026-05-26","cited_by_count":2,"area":"agents"},{"id":"2606.22417","title":"Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent","created":"2026-06-21","cited_by_count":2,"area":"agents"},{"id":"2608.09072","title":"A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents","created":"2026-08-10","cited_by_count":2,"area":"agents"},{"id":"2609.04611","title":"$\\tau^\\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction","created":"2026-09-04","cited_by_count":2,"area":"agents"},{"id":"2510.17158","title":"Integrating Performance Tools in Model Reasoning for GPU Kernel Optimization","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2512.16956","title":"SpIDER: Spatially Informed Dense Embedding Retrieval for Software Issue Localization","created":"2025-12-18","cited_by_count":1,"area":"agents"},{"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":"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":"2603.11356","title":"Resolving Java Code Repository Issues with iSWE Agent","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2606.13763","title":"Do programming languages still matter to your AI coding agent teammate? Evidence at scale from chess engines","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2606.25514","title":"Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolution","created":"2026-06-24","cited_by_count":1,"area":"agents"},{"id":"2607.10569","title":"When Does Restricting a Coding Agent to execute_code Help? A Regime $\\times$ Agent-Design Ablation","created":"2026-07-12","cited_by_count":1,"area":"agents"},{"id":"2607.27409","title":"SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2607.28587","title":"PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2609.06780","title":"Shortcutting the Fix: Identifying and Categorizing Agentic Exploits in Software Engineering Benchmarks","created":"2026-09-06","cited_by_count":1,"area":"agents"},{"id":"2609.33763","title":"SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2507.13499","title":"AI-Assisted Fixes to Code Review Comments at Scale","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2602.13921","title":"GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.24946","title":"MobileDev-Bench: A Benchmark for Issue Resolution in Mobile Application Development","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.09564","title":"ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness","created":"2026-02-14","cited_by_count":0,"area":"agents"},{"id":"2605.26100","title":"Beyond Summaries: Structure-Aware Labeling of Code Changes with Large Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.08500","title":"Projecting the Emerging Mindset of SWE Agent by Launching a Wild Code Understanding Journey","created":"2026-06-07","cited_by_count":0,"area":"agents"},{"id":"2607.00700","title":"LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.21760","title":"Bespoke Visual Assistance: What and How do Blind and Low-Vision People Create with Agentic Programming?","created":"2026-07-23","cited_by_count":0,"area":"agents"},{"id":"2607.26451","title":"ExplainBench: Evaluating Code Explanations from Agents","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2608.14838","title":"The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.27831","title":"RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.10416","title":"TrajMark: Ownership Attribution and Segment-Level Tamper Localization for Coding-Agent Trajectories","created":"2026-09-09","cited_by_count":0,"area":"agents"},{"id":"2609.29465","title":"SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.29754","title":"SWE-PolyVision: Benchmarking Cross-Image Abductive Reasoning for Repository-Level Software Engineering","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2609.32662","title":"AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.02163","title":"AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.06193","title":"Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.11559","title":"SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.11578","title":"Chronos Enables Code Agents to Reason over Software Evolution","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.12569","title":"SWE-Duel: Towards a Self-Scaling Arena for Coding Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.13395","title":"ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.18206","title":"SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}