{"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/dynamic-llm-agent-network-an-llm-agent","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","arxiv_id":"2310.02170","date":"2023-10-03","proceeding":null,"authors":["Zijun Liu","Yanzhe Zhang","Peng Li","Yang Liu","Diyi Yang"],"abstract":"Recent studies show that collaborating multiple large language model (LLM) powered agents is a promising way for task solving. However, current approaches are constrained by using a fixed number of agents and static communication structures. In this work, we propose automatically selecting a team of agents from candidates to collaborate in a dynamic communication structure toward different tasks and domains. Specifically, we build a framework named Dynamic LLM-Powered Agent Network ($\\textbf{DyLAN}$) for LLM-powered agent collaboration, operating a two-stage paradigm: (1) Team Optimization and (2) Task Solving. During the first stage, we utilize an $\\textit{agent selection}$ algorithm, based on an unsupervised metric called $\\textit{Agent Importance Score}$, enabling the selection of best agents according to their contributions in a preliminary trial, oriented to the given task. Then, in the second stage, the selected agents collaborate dynamically according to the query. Empirically, we demonstrate that DyLAN outperforms strong baselines in code generation, decision-making, general reasoning, and arithmetic reasoning tasks with moderate computational cost. On specific subjects in MMLU, selecting a team of agents in the team optimization stage improves accuracy by up to 25.0% in DyLAN.","url_abs":"https://arxiv.org/abs/2310.02170v2","url_pdf":"https://arxiv.org/pdf/2310.02170v2.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":"dynamic-llm-agent-network-an-llm-agent","repo_url":"https://github.com/salt-nlp/dylan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"humaneval","task_name":"HumanEval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"mmlu","task_name":"MMLU"},{"task_slug":"math","task_name":"Math"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.02170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02170"}},"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/salt-nlp/dylan","reach":null}],"summary":{"ran_draft_wrong":2,"ran_violates":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"52487c571369c8c3","entry":"parse_bullets","repo":"salt-nlp/dylan","repo_kind":"official","path":"code/MATH/eval_math.py","file_url":"https://github.com/salt-nlp/dylan/blob/HEAD/code/MATH/eval_math.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52487c571369c8c3"}},{"code_sha256_prefix":"efece58874c297b1","entry":"parse_yes_no","repo":"salt-nlp/dylan","repo_kind":"official","path":"code/MATH/eval_math.py","file_url":"https://github.com/salt-nlp/dylan/blob/HEAD/code/MATH/eval_math.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"efece58874c297b1"}},{"code_sha256_prefix":"8fce0277228f26b2","entry":"solve_math_problems","repo":"salt-nlp/dylan","repo_kind":"official","path":"code/MATH/eval_math.py","file_url":"https://github.com/salt-nlp/dylan/blob/HEAD/code/MATH/eval_math.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8fce0277228f26b2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}