{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/language-agents-as-optimizable-graphs","title":"Language Agents as Optimizable Graphs","arxiv_id":"2402.16823","date":"2024-02-26","proceeding":null,"authors":["Mingchen Zhuge","Wenyi Wang","Louis Kirsch","Francesco Faccio","Dmitrii Khizbullin","Jürgen Schmidhuber"],"abstract":"Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. The nodes implement functions to process multimodal data or query LLMs, and the edges describe the information flow between operations. Graphs can be recursively combined into larger composite graphs representing hierarchies of inter-agent collaboration (where edges connect operations of different agents). Our novel automatic graph optimizers (1) refine node-level LLM prompts (node optimization) and (2) improve agent orchestration by changing graph connectivity (edge optimization). Experiments demonstrate that our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents. The code can be found at https://github.com/metauto-ai/gptswarm.","url_abs":"https://arxiv.org/abs/2402.16823v3","url_pdf":"https://arxiv.org/pdf/2402.16823v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"language-agents-as-optimizable-graphs","repo_url":"https://github.com/metauto-ai/gptswarm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-agents-as-optimizable-graphs","repo_url":"https://github.com/lukasvierling/dynamicgptswarm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.16823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16823"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lukasvierling/dynamicgptswarm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/metauto-ai/gptswarm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"30f808af7f9e8778","entry":"load_config","repo":"lukasvierling/dynamicgptswarm","repo_kind":"listed","path":"experiments/run_gaia.py","file_url":"https://github.com/lukasvierling/dynamicgptswarm/blob/HEAD/experiments/run_gaia.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30f808af7f9e8778"}},{"code_sha256_prefix":"2dd39bccea7e9386","entry":"load_result","repo":"metauto-ai/gptswarm","repo_kind":"official","path":"experiments/run_humaneval.py","file_url":"https://github.com/metauto-ai/gptswarm/blob/HEAD/experiments/run_humaneval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2dd39bccea7e9386"}},{"code_sha256_prefix":"74907f2448ff71f2","entry":"batched_evaluator","repo":"metauto-ai/gptswarm","repo_kind":"official","path":"experiments/crosswords/evaluate.py","file_url":"https://github.com/metauto-ai/gptswarm/blob/HEAD/experiments/crosswords/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74907f2448ff71f2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}