{"list":"closest","total":57,"rows":[{"id":"2608.08654","title":"The Scaffolding Matters More Than the Interface: A Controlled Comparison of MCP and CLI Tool Use Across Seven Agent Scaffoldings, Five Language Models, and One Software Task","created":"2026-08-09","cited_by_count":2},{"id":"2608.06113","title":"DCAS: Decoupling CLI Agent Scaffolding to Internalize Planning across Scaffolds","created":"2026-08-06","cited_by_count":3},{"id":"2608.02670","title":"Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments","created":"2026-08-02","cited_by_count":3},{"id":"2607.09510","title":"Failure as a Process: An Anatomy of CLI Coding Agent Trajectories","created":"2026-07-10","cited_by_count":13},{"id":"2607.02294","title":"Coding Agents Are Guessing: Measuring Action-Boundary Violations in Underspecified DevOps Instructions","created":"2026-07-02","cited_by_count":10},{"id":"2607.22585","title":"The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation","created":"2026-06-08","cited_by_count":12},{"id":"2606.08960","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops","created":"2026-06-08","cited_by_count":9},{"id":"2605.20251","title":"ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents","created":"2026-05-18","cited_by_count":6},{"id":"2605.12729","title":"Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety","created":"2026-05-12","cited_by_count":2},{"id":"2605.08715","title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","created":"2026-05-09","cited_by_count":11},{"id":"2604.25850","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","created":"2026-04-28","cited_by_count":142},{"id":"2604.23581","title":"AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking","created":"2026-04-26","cited_by_count":9},{"id":"2604.09678","title":"NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network Configuration","created":"2026-04-03","cited_by_count":5},{"id":"2604.02547","title":"Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure","created":"2026-04-02","cited_by_count":11},{"id":"2604.01527","title":"REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage","created":"2026-04-02","cited_by_count":5},{"id":"2604.00594","title":"Agent psychometrics: Task-level performance prediction in agentic coding benchmarks","created":"2026-04-01","cited_by_count":11},{"id":"2604.00073","title":"Terminal Agents Suffice for Enterprise Automation","created":"2026-03-31","cited_by_count":6},{"id":"2603.24755","title":"SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks","created":"2026-03-25","cited_by_count":30},{"id":"2603.21489","title":"Effective Strategies for Asynchronous Software Engineering Agents","created":"2026-03-23","cited_by_count":16},{"id":"2603.21357","title":"AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling","created":"2026-03-22","cited_by_count":13},{"id":"2603.20691","title":"SWE-Next: Scalable Real-World Software Engineering Tasks for Agents","created":"2026-03-21","cited_by_count":9},{"id":"2603.17104","title":"When the Specification Emerges: Benchmarking Faithfulness Loss in Long-Horizon Coding Agents","created":"2026-03-17","cited_by_count":6},{"id":"2603.15401","title":"SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?","created":"2026-03-16","cited_by_count":82},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18},{"id":"2603.00575","title":"SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks","created":"2026-02-28","cited_by_count":4},{"id":"2602.23866","title":"SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale","created":"2026-02-27","cited_by_count":29},{"id":"2602.22518","title":"RepoMod-Bench: A Benchmark for Code Repository Modernization via Implementation-Agnostic Testing","created":"2026-02-26","cited_by_count":3},{"id":"2602.19594","title":"ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads?","created":"2026-02-23","cited_by_count":6},{"id":"2602.10999","title":"CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion","created":"2026-02-11","cited_by_count":23},{"id":"2602.06593","title":"AgentStepper: Interactive Debugging of Software Development Agents","created":"2026-02-06","cited_by_count":9},{"id":"2602.03411","title":"SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training","created":"2026-02-03","cited_by_count":22},{"id":"2602.01655","title":"ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development","created":"2026-02-02","cited_by_count":12},{"id":"2602.01465","title":"Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering","created":"2026-02-01","cited_by_count":7},{"id":"2602.01244","title":"Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments","created":"2026-02-01","cited_by_count":33},{"id":"2602.00592","title":"DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder","created":"2026-01-31","cited_by_count":3},{"id":"2601.18418","title":"daVinci-Dev: Agent-native Mid-training for Software Engineering","created":"2026-01-26","cited_by_count":18},{"id":"2601.10343","title":"OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding","created":"2026-01-15","cited_by_count":15},{"id":"2601.00477","title":"Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub","created":"2026-01-01","cited_by_count":7},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59},{"id":"2512.20660","title":"The Dual-State Architecture for Reliable LLM Agents","created":"2025-12-18","cited_by_count":3},{"id":"2512.12730","title":"NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents","created":"2025-12-14","cited_by_count":65},{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95},{"id":"2511.03690","title":"The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents","created":"2025-11-05","cited_by_count":45},{"id":"2510.08996","title":"Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation","created":"2025-10-10","cited_by_count":15},{"id":"2509.25370","title":"Where LLM Agents Fail and How They can Learn From Failures","created":"2025-09-29","cited_by_count":133},{"id":"2509.23045","title":"Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents","created":"2025-09-27","cited_by_count":41},{"id":"2509.01245","title":"Towards Agentic OS: An LLM Agent Framework for Linux Schedulers","created":"2025-09-01","cited_by_count":2},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28},{"id":"2508.00083","title":"A Survey on Code Generation with LLM-based Agents","created":"2025-07-31","cited_by_count":106},{"id":"2507.09063","title":"SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments","created":"2025-07-11","cited_by_count":18},{"id":"2506.16650","title":"SemAgent: A Semantics Aware Program Repair Agent","created":"2025-06-19","cited_by_count":9},{"id":"2506.08311","title":"Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study","created":"2025-06-10","cited_by_count":16},{"id":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19},{"id":"2412.21139","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","created":"2024-12-30","cited_by_count":336},{"id":"2409.16299","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","created":"2024-09-09","cited_by_count":61},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564}],"next_cursor":null}