{"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/benchmark-self-evolving-a-multi-agent","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","arxiv_id":"2402.11443","date":"2024-02-18","proceeding":null,"authors":["Siyuan Wang","Zhuohan Long","Zhihao Fan","Zhongyu Wei","Xuanjing Huang"],"abstract":"This paper presents a benchmark self-evolving framework to dynamically evaluate rapidly advancing Large Language Models (LLMs), aiming for a more accurate assessment of their capabilities and limitations. We utilize a multi-agent system to manipulate the context or question of original instances, reframing new evolving instances with high confidence that dynamically extend existing benchmarks. Towards a more scalable, robust and fine-grained evaluation, we implement six reframing operations to construct evolving instances testing LLMs against diverse queries, data noise and probing their problem-solving sub-abilities. With this framework, we extend benchmark datasets of four tasks. Experimental results show a general performance decline in most LLMs against their original results. This decline under our scalable and robust evaluations, alongside our fine-grained evaluation, more accurately reflect models' capabilities. Besides, our framework widens performance discrepancies both between different models and within the same model across various tasks, facilitating more informed model selection for specific tasks (Code and data are available at https://github.com/NanshineLoong/Self-Evolving-Benchmark).","url_abs":"https://arxiv.org/abs/2402.11443v1","url_pdf":"https://arxiv.org/pdf/2402.11443v1.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":"benchmark-self-evolving-a-multi-agent","repo_url":"https://github.com/nanshineloong/self-evolving-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model-selection","task_name":"Model Selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.11443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11443"}},"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/nanshineloong/self-evolving-benchmark","reach":{"status":"ok"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":9,"samples":[{"code_sha256_prefix":"d30ff74f08972e4b","entry":"clear_sign","repo":"nanshineloong/self-evolving-benchmark","repo_kind":"official","path":"utils/judge_result.py","file_url":"https://github.com/nanshineloong/self-evolving-benchmark/blob/HEAD/utils/judge_result.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d30ff74f08972e4b"}},{"code_sha256_prefix":"0f6e3db7a923e538","entry":"construct_mistral_string_prompt","repo":"nanshineloong/self-evolving-benchmark","repo_kind":"official","path":"utils/call_llm.py","file_url":"https://github.com/nanshineloong/self-evolving-benchmark/blob/HEAD/utils/call_llm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f6e3db7a923e538"}},{"code_sha256_prefix":"77f7f2e99f715477","entry":"get_problem","repo":"nanshineloong/self-evolving-benchmark","repo_kind":"official","path":"gen_dataset.py","file_url":"https://github.com/nanshineloong/self-evolving-benchmark/blob/HEAD/gen_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77f7f2e99f715477"}},{"code_sha256_prefix":"8697a7385d94c099","entry":"judge_strategyqa_result","repo":"nanshineloong/self-evolving-benchmark","repo_kind":"official","path":"utils/judge_result.py","file_url":"https://github.com/nanshineloong/self-evolving-benchmark/blob/HEAD/utils/judge_result.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8697a7385d94c099"}},{"code_sha256_prefix":"552e465f43a9c8f3","entry":"set_up_clutrr_input_list","repo":"nanshineloong/self-evolving-benchmark","repo_kind":"official","path":"utils/construction.py","file_url":"https://github.com/nanshineloong/self-evolving-benchmark/blob/HEAD/utils/construction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"552e465f43a9c8f3"}},{"code_sha256_prefix":"3882d49a19bd4e9f","entry":"set_up_gsm8k_input_list","repo":"nanshineloong/self-evolving-benchmark","repo_kind":"official","path":"utils/construction.py","file_url":"https://github.com/nanshineloong/self-evolving-benchmark/blob/HEAD/utils/construction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3882d49a19bd4e9f"}},{"code_sha256_prefix":"157eb62086297c7c","entry":"set_up_strategyqa_input_list","repo":"nanshineloong/self-evolving-benchmark","repo_kind":"official","path":"utils/construction.py","file_url":"https://github.com/nanshineloong/self-evolving-benchmark/blob/HEAD/utils/construction.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"157eb62086297c7c"}},{"code_sha256_prefix":"660bc1889994d7ca","entry":"to_string","repo":"nanshineloong/self-evolving-benchmark","repo_kind":"official","path":"gen_dataset.py","file_url":"https://github.com/nanshineloong/self-evolving-benchmark/blob/HEAD/gen_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"660bc1889994d7ca"}},{"code_sha256_prefix":"a79ee845c55fc23b","entry":"get_openai_response","repo":"nanshineloong/self-evolving-benchmark","repo_kind":"official","path":"utils/call_llm.py","file_url":"https://github.com/nanshineloong/self-evolving-benchmark/blob/HEAD/utils/call_llm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a79ee845c55fc23b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}