{"work":{"id":"01826cd9-a652-403c-a2ec-531da9fe2b6a","openalex_id":null,"doi":null,"arxiv_id":"2405.15793","raw_key":null,"title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","authors":null,"authors_text":"John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan","year":2024,"venue":"cs.SE","abstract":"Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software engineering, we posit that LM agents represent a new category of end users with their own needs and abilities, and would benefit from specially-built interfaces to the software they use. We investigate how interface design affects the performance of language model agents. As a result of this exploration, we introduce SWE-agent: a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively, far exceeding the previous state-of-the-art achieved with non-interactive LMs. Finally, we provide insight on how the design of the ACI can impact agents' behavior and performance.","external_url":"https://arxiv.org/abs/2405.15793","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-23T19:08:20.790103+00:00","pith_arxiv_id":"2405.15793","created_at":"2026-05-09T22:29:06.434041+00:00","updated_at":"2026-05-23T19:08:20.790103+00:00","title_quality_ok":true,"display_title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","render_title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering"},"hub":{"state":{"work_id":"01826cd9-a652-403c-a2ec-531da9fe2b6a","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":86,"external_cited_by_count":null,"distinct_field_count":13,"first_pith_cited_at":"2024-07-01T17:24:45+00:00","last_pith_cited_at":"2026-05-21T16:06:34+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-30T18:21:23.107871+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":22},{"context_role":"method","n":2},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":20},{"context_polarity":"use_method","n":2},{"context_polarity":"baseline","n":1},{"context_polarity":"support","n":1},{"context_polarity":"unclear","n":1}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T14:01:13.935402+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","work_id":"f1762ea0-e382-4f38-a28c-adc643789859","shared_citers":18},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":13},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":11},{"title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","work_id":"d0effe15-a689-441a-8e3f-ea35f1c4e4b1","shared_citers":10},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":9},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":8},{"title":"Agentless: Demystifying LLM-based Software Engineering Agents","work_id":"71c901c4-3c83-4e10-af54-3daef7fff397","shared_citers":7},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":7},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":7},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":6},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":6},{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":6},{"title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","work_id":"56b6b58d-e73a-4317-896e-36ac5f84e957","shared_citers":6},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":6},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":6},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":5},{"title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","work_id":"a561c78a-4b02-4053-a92a-bc5c7c5f6b9b","shared_citers":5},{"title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","work_id":"3c555b48-a4d9-42dd-9fdd-0f6018fbe9cb","shared_citers":5},{"title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","work_id":"7058ffd2-a339-4102-89eb-248eeb074652","shared_citers":5},{"title":"A-MEM: Agentic Memory for LLM Agents","work_id":"3b98feb2-fdb1-479a-bbe4-2c298a4592e2","shared_citers":4},{"title":"arXiv preprint arXiv:2603.07670 (2026)","work_id":"9aecac84-4c67-4c0c-80b2-942f93760de7","shared_citers":4},{"title":"AutoCodeRover : Autonomous program improvement","work_id":"fa93e782-fee4-4c22-9486-d9d5d62f7b93","shared_citers":4},{"title":"Concrete Problems in AI Safety","work_id":"c8d14fbe-6eab-464a-95b3-778aabd82fa3","shared_citers":4},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":4}],"time_series":[{"n":1,"year":2024},{"n":1,"year":2025},{"n":47,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T14:01:12.013577+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T14:01:20.626297+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","claims":[{"claim_text":"Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software engineering, we posit that LM agents represent a new category of end users with their own needs and abilities, and would benefit from specially-built interfaces to the software they use. We investigate how interface design affects the performance of language model agents. As a result of this exploration, we introduce SWE-agent: a system that facilitat","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T14:01:13.937652+00:00"}},"summary":{"title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","claims":[{"claim_text":"Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software engineering, we posit that LM agents represent a new category of end users with their own needs and abilities, and would benefit from specially-built interfaces to the software they use. We investigate how interface design affects the performance of language model agents. As a result of this exploration, we introduce SWE-agent: a system that facilitat","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","work_id":"f1762ea0-e382-4f38-a28c-adc643789859","shared_citers":18},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":13},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":11},{"title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","work_id":"d0effe15-a689-441a-8e3f-ea35f1c4e4b1","shared_citers":10},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":9},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":8},{"title":"Agentless: Demystifying LLM-based Software Engineering Agents","work_id":"71c901c4-3c83-4e10-af54-3daef7fff397","shared_citers":7},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":7},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":7},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":6},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":6},{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":6},{"title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","work_id":"56b6b58d-e73a-4317-896e-36ac5f84e957","shared_citers":6},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":6},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":6},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":5},{"title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","work_id":"a561c78a-4b02-4053-a92a-bc5c7c5f6b9b","shared_citers":5},{"title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","work_id":"3c555b48-a4d9-42dd-9fdd-0f6018fbe9cb","shared_citers":5},{"title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","work_id":"7058ffd2-a339-4102-89eb-248eeb074652","shared_citers":5},{"title":"A-MEM: Agentic Memory for LLM Agents","work_id":"3b98feb2-fdb1-479a-bbe4-2c298a4592e2","shared_citers":4},{"title":"arXiv preprint arXiv:2603.07670 (2026)","work_id":"9aecac84-4c67-4c0c-80b2-942f93760de7","shared_citers":4},{"title":"AutoCodeRover : Autonomous program improvement","work_id":"fa93e782-fee4-4c22-9486-d9d5d62f7b93","shared_citers":4},{"title":"Concrete Problems in AI Safety","work_id":"c8d14fbe-6eab-464a-95b3-778aabd82fa3","shared_citers":4},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":4}],"time_series":[{"n":1,"year":2024},{"n":1,"year":2025},{"n":47,"year":2026}],"dependency_candidates":[]},"authors":[]}}