{"total":81,"rows":[{"id":"2604.20779","title":"SWE-chat: Coding Agent Interactions From Real Users in the Wild","created":"2026-04-22","cited_by_count":43,"area":"agents"},{"id":"2511.00197","title":"Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories","created":"2025-10-31","cited_by_count":33,"area":"agents"},{"id":"2601.18341","title":"Agentic Much? Adoption of Coding Agents on GitHub","created":"2026-01-26","cited_by_count":32,"area":"agents"},{"id":"2606.06324","title":"From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws","created":"2026-06-04","cited_by_count":29,"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":"2512.02393","title":"Process-Centric Analysis of Agentic Software Systems","created":"2025-12-02","cited_by_count":24,"area":"agents"},{"id":"2602.23701","title":"From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems","created":"2026-02-27","cited_by_count":19,"area":"agents"},{"id":"2604.03515","title":"Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures","created":"2026-04-03","cited_by_count":18,"area":"agents"},{"id":"2604.11641","title":"CodeTracer: Towards Traceable Agent States","created":"2026-04-13","cited_by_count":16,"area":null},{"id":"2602.17037","title":"Wink: Recovering from Misbehaviors in Coding Agents","created":"2026-02-19","cited_by_count":15,"area":"agents"},{"id":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2605.03378","title":"ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection","created":"2026-05-05","cited_by_count":14,"area":"agents"},{"id":"2607.09510","title":"Failure as a Process: An Anatomy of CLI Coding Agent Trajectories","created":"2026-07-10","cited_by_count":13,"area":"agents"},{"id":"2606.00765","title":"FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search","created":"2026-05-30","cited_by_count":12,"area":"lr"},{"id":"2604.02547","title":"Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure","created":"2026-04-02","cited_by_count":11,"area":"lr"},{"id":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","cited_by_count":11,"area":"agents"},{"id":"2602.06593","title":"AgentStepper: Interactive Debugging of Software Development Agents","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"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":"2601.15232","title":"When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling","created":"2026-01-21","cited_by_count":6,"area":"agents"},{"id":"2601.18345","title":"Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity","created":"2026-01-26","cited_by_count":6,"area":"agents"},{"id":"2601.19066","title":"Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair","created":"2026-01-27","cited_by_count":6,"area":"agents"},{"id":"2602.00409","title":"Are Coding Agents Generating Over-Mocked Tests? An Empirical Study","created":"2026-01-30","cited_by_count":6,"area":"agents"},{"id":"2605.07509","title":"MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals","created":"2026-05-08","cited_by_count":6,"area":"agents"},{"id":"2606.05391","title":"Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2603.24631","title":"Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code","created":"2026-03-25","cited_by_count":5,"area":"agents"},{"id":"2606.15874","title":"LLM-as-Code: Agentic Programming for Agent Harness","created":"2026-06-14","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":"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":"2603.05744","title":"CodeScout: Contextual Problem Statement Enhancement for Software Agents","created":"2026-03-05","cited_by_count":4,"area":"agents"},{"id":"2605.08717","title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","created":"2026-05-09","cited_by_count":4,"area":null},{"id":"2605.18332","title":"Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents","created":"2026-05-18","cited_by_count":4,"area":"agents"},{"id":"2606.22741","title":"GRADE: Graph Representation of LLM Agent Dependency and Execution","created":"2026-06-22","cited_by_count":4,"area":"agents"},{"id":"2608.00808","title":"Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents","created":"2026-08-01","cited_by_count":4,"area":"agents"},{"id":"2511.08475","title":"Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale","created":"2025-11-11","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":"2608.12355","title":"Humans are Missing from AI Coding Agent Research","created":"2026-07-04","cited_by_count":3,"area":"agents"},{"id":"2511.11012","title":"Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair","created":"2025-11-14","cited_by_count":2,"area":"agents"},{"id":"2512.23844","title":"From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering","created":"2025-12-29","cited_by_count":2,"area":"agents"},{"id":"2602.04640","title":"Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents","created":"2026-02-04","cited_by_count":2,"area":"agents"},{"id":"2605.15222","title":"PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2606.22110","title":"TraceView: Interactive Visualization of Agentic Program Repair Trajectories","created":"2026-06-20","cited_by_count":2,"area":"agents"},{"id":"2607.06195","title":"LogicHunter: Testing LLM Agent Frameworks with an Agentic Oracle","created":"2026-07-07","cited_by_count":2,"area":"agents"},{"id":"2607.10856","title":"How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"id":"2608.08413","title":"Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications","created":"2026-08-09","cited_by_count":2,"area":"agents"},{"id":"2510.16059","title":"SIADAFIX: issue description response for adaptive program repair","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2602.02138","title":"CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems","created":"2026-02-02","cited_by_count":1,"area":"agents"},{"id":"2603.09004","title":"Can AI Agents Generate Microservices? How Far are We?","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2604.01437","title":"Reproducible, Explainable, and Effective Evaluations of Agentic AI for Software Engineering","created":"2026-04-01","cited_by_count":1,"area":"agents"},{"id":"2604.07720","title":"Towards Knowledgeable Deep Research: Framework and Benchmark","created":"2026-04-09","cited_by_count":1,"area":"agents"},{"id":"2604.07789","title":"ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents","created":"2026-04-09","cited_by_count":1,"area":"agents"},{"id":"2605.24138","title":"Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2607.05188","title":"Latent Programming Horizons in Coding Agents","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2607.09065","title":"Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2607.22807","title":"The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2607.24604","title":"Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2608.09253","title":"SkillSentry: Reliable Skill Execution for LLM Agents via Runtime Assurance","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.13598","title":"Measuring Cross-Task Behavioral Consistency in Language Model Agents","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2608.16630","title":"The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks","created":"2026-08-17","cited_by_count":1,"area":"agents"},{"id":"2601.18119","title":"Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.04445","title":"AgenticAKM : Enroute to Agentic Architecture Knowledge Management","created":"2026-02-04","cited_by_count":0,"area":"agents"},{"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":"2607.02882","title":"Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.04974","title":"A Comprehensive Study of Implementation Bugs in Multi-modal Agents","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.23624","title":"Where Is the Tradeoff in Using Third-Party API Routers for Agentic Software Development?","created":"2026-07-26","cited_by_count":0,"area":"agents"},{"id":"2607.28871","title":"Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2608.05026","title":"ArtAnno: Annotating Implicit Semantics in Artworks through LLM Agent-Driven Bidirectional Human-AI Augmentation","created":"2026-08-05","cited_by_count":0,"area":"agents"},{"id":"2608.10934","title":"Understanding the Architecture of Coding Agents: An Exploratory Study Using a Research Prototype","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.16411","title":"Towards Risk-free AI Agent Deployment","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2608.21310","title":"Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.27969","title":"openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.04909","title":"Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.20301","title":"AgentPProf: Semantic Profiler for Long Horizon AI Agents","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.24928","title":"Trajectory-Aware Benchmark Subset Selection for Cost-Efficient Software Engineering Agent Regression Testing","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.30725","title":"Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.37864","title":"AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.04375","title":"Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.04716","title":"Towards Automatically Pruning Logging Code with Coding Agents: How Far Are We?","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.06001","title":"AgentSpy: Making AI Agent Behavior Observable","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.06163","title":"Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair","created":"2026-10-05","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}