# Software engineering coding agents Area: [LLM agents and tool use](https://mlsanity.com/agents/index.md). HTML: https://mlsanity.com/agents/software-engineering-coding-agents/ ## Key facts - Software engineering coding agents: 2,041 papers on arXiv since 2023 (data through 7 Oct 2026). - 540 of its 2,041 mapped papers (26%) cite “SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering” (2024, arXiv 2405.15793). - 312 of its 2,041 mapped papers (15%) cite “OpenHands: An Open Platform for AI Software Developers as Generalist Agents” (2024, arXiv 2407.16741). - 201 new papers 17 Sep–7 Oct. ## Most cited here - [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024), cited by 540 papers here - [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024), cited by 312 papers here - [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023), cited by 192 papers here - [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023), cited by 154 papers here - [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024), cited by 152 papers here - [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025), cited by 119 papers here - [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024), cited by 102 papers here - [AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation](https://mlsanity.com/paper/2312.13010/) (2023), cited by 95 papers here - [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024), cited by 93 papers here - [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024), cited by 91 papers here ## New (17 Sep–7 Oct) - [Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study](https://mlsanity.com/paper/2610.10961/) (2026-10-07) - [The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate](https://mlsanity.com/paper/2610.10629/) (2026-10-07) - [Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking](https://mlsanity.com/paper/2610.10628/) (2026-10-07) - [TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution](https://mlsanity.com/paper/2610.10619/) (2026-10-07) - [Code Understanding is a Bottleneck for Coding Agents](https://mlsanity.com/paper/2610.10610/) (2026-10-07) - [Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation](https://mlsanity.com/paper/2610.10604/) (2026-10-07) - [Why Software Engineering Is Indispensable in the Age of Coding Agents](https://mlsanity.com/paper/2610.10226/) (2026-10-07) - [Know the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM Failures](https://mlsanity.com/paper/2610.10126/) (2026-10-07) - [Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification](https://mlsanity.com/paper/2610.09681/) (2026-10-07) - [Coding-Agent Benchmarks Should Match Their Users' Task Flows](https://mlsanity.com/paper/2610.09633/) (2026-10-07) - [We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents](https://mlsanity.com/paper/2610.09243/) (2026-10-07) - [A Survey on LLM-Integrated Hardware Design Verification](https://mlsanity.com/paper/2610.10580/) (2026-10-06) - [GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks](https://mlsanity.com/paper/2610.09112/) (2026-10-06) - [RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents](https://mlsanity.com/paper/2610.09088/) (2026-10-06) - [Large-scale Repository Engineering via Agent-Native Reusable Code Primitives](https://mlsanity.com/paper/2610.09079/) (2026-10-06) - [Humanize: Judgement Engineering for Agentic Coding](https://mlsanity.com/paper/2610.08900/) (2026-10-06) - [ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences](https://mlsanity.com/paper/2610.08691/) (2026-10-06) - [ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding](https://mlsanity.com/paper/2610.08662/) (2026-10-06) - [A Case Study in Assuring AI-Written Software](https://mlsanity.com/paper/2610.08651/) (2026-10-06) - [SquidAgent: Parallelize Wisely, Coordinate Efficiently](https://mlsanity.com/paper/2610.08647/) (2026-10-06) - [Agentic RCA for Internet-Scale Services Using Constrained Creativity](https://mlsanity.com/paper/2610.08622/) (2026-10-06) - [FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents](https://mlsanity.com/paper/2610.07898/) (2026-10-06) - [OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow Generation](https://mlsanity.com/paper/2610.07787/) (2026-10-06) - [Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale](https://mlsanity.com/paper/2610.07289/) (2026-10-05) - [Verifying Coordination in Parallel Coding Agents: NP-Bench and a Scheduling Planner](https://mlsanity.com/paper/2610.07261/) (2026-10-05) - [MemMux: Runtime Verification and Honest Resource Attribution for Fleets of Parallel Coding Agents](https://mlsanity.com/paper/2610.07257/) (2026-10-05) - [Evaluating Inference Compute for Generative AI: A Framework for Enterprise Workloads](https://mlsanity.com/paper/2610.07094/) (2026-10-05) - [Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification](https://mlsanity.com/paper/2610.06790/) (2026-10-05) - [Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving](https://mlsanity.com/paper/2610.06597/) (2026-10-05) - [Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents](https://mlsanity.com/paper/2610.06193/) (2026-10-05)