{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/optimizing-model-selection-for-compound-ai","title":"Optimizing Model Selection for Compound AI Systems","arxiv_id":"2502.14815","date":"2025-02-20","proceeding":null,"authors":["Lingjiao Chen","Jared Quincy Davis","Boris Hanin","Peter Bailis","Matei Zaharia","James Zou","Ion Stoica"],"abstract":"Compound AI systems that combine multiple LLM calls, such as self-refine and multi-agent-debate, achieve strong performance on many AI tasks. We address a core question in optimizing compound systems: for each LLM call or module in the system, how should one decide which LLM to use? We show that these LLM choices have a large effect on quality, but the search space is exponential. We propose LLMSelector, an efficient framework for model selection in compound systems, which leverages two key empirical insights: (i) end-to-end performance is often monotonic in how well each module performs, with all other modules held fixed, and (ii) per-module performance can be estimated accurately by an LLM. Building upon these insights, LLMSelector iteratively selects one module and allocates to it the model with the highest module-wise performance, as estimated by an LLM, until no further gain is possible. LLMSelector is applicable to any compound system with a bounded number of modules, and its number of API calls scales linearly with the number of modules, achieving high-quality model allocation both empirically and theoretically. Experiments with popular compound systems such as multi-agent debate and self-refine using LLMs such as GPT-4o, Claude 3.5 Sonnet and Gemini 1.5 show that LLMSelector confers 5%-70% accuracy gains compared to using the same LLM for all modules.","url_abs":"https://arxiv.org/abs/2502.14815v1","url_pdf":"https://arxiv.org/pdf/2502.14815v1.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":"optimizing-model-selection-for-compound-ai","repo_url":"https://github.com/LLMSELECTOR/LLMSELECTOR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.14815","atlas_url":"https://app.syntology.ai/?focus=2502.14815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14815"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.14815"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.14815"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.14815\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2502.14815"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2502.14815\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2502.14815"},"call":"get_concepts_for_paper(arxiv_id=\"2502.14815\")"}],"by_repo":[{"repo":"LLMSELECTOR/LLMSELECTOR","kind":"official","samples":10,"ran":10,"instrument":1,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2502.14815.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2502.14815.svg"},"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/LLMSELECTOR/LLMSELECTOR","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":9,"ran_draft_wrong":1},"n_samples":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":10,"ran":10,"n_ran_checked":9,"n_instrument":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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":10,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"96362ca151f15497","code_sha256_prefix":"96362ca151f15497","entry":"Get_Generate","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/llm.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/llm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"prompt:str/0/str, model_gen:str/0/str, stop:NoneType/0/?, max_tokens:int/0/int, temperature:float/0/float, query_images:NoneType/0/?","fixture_out_type":"str","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"96362ca151f15497"}},{"code_sha256":"075a2a4962fab858","code_sha256_prefix":"075a2a4962fab858","entry":"compute_score","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/metric.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"compoundaisystems:dict/0/?, data_df:DataFrame/0/?, metric:MockMetric/0/?, true_answer_name:str/0/str, save_answer_prefix:str/0/str, answer_convert:callable/0/?","fixture_out_type":"DataFrame","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":"/code/compute-score","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"075a2a4962fab858"}},{"code_sha256":"1a27128efa695483","code_sha256_prefix":"1a27128efa695483","entry":"compute_tag","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/metric.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"compoundaisystems:dict/0/?, data_df:DataFrame/0/?, metric:str/0/str, tag:str/0/str","fixture_out_type":"DataFrame","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1a27128efa695483"}},{"code_sha256":"ae7782a357cf3a90","code_sha256_prefix":"ae7782a357cf3a90","entry":"extract_ans","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/module/debate.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/module/debate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"text:str/0/str, regex:str/0/str, remove_left:int/0/int, remove_right:int/0/int","fixture_out_type":"str","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":"/code/extract-ans","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ae7782a357cf3a90"}},{"code_sha256":"4ec0ffdf43c1c1c5","code_sha256_prefix":"4ec0ffdf43c1c1c5","entry":"extract_ans","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/module/majorityvote.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/module/majorityvote.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"text:str/0/str, regex:str/0/str, remove_left:int/0/int, remove_right:int/0/int","fixture_out_type":"str","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":"/code/extract-ans","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4ec0ffdf43c1c1c5"}},{"code_sha256":"5672cff2de3b190b","code_sha256_prefix":"5672cff2de3b190b","entry":"extract_final_answer","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/diagnoser.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/diagnoser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"text:str/0/str","fixture_out_type":"int","level_recorded_at":"2026-09-25T04:00:33.621019+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5672cff2de3b190b"},"code_page":"/code/extract-final-answer","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5672cff2de3b190b"}},{"code_sha256":"05b617dbf3b25a2a","code_sha256_prefix":"05b617dbf3b25a2a","entry":"my_decode","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/llm.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/llm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"obj:bytes/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"05b617dbf3b25a2a"}},{"code_sha256":"f2fc23dea676ed77","code_sha256_prefix":"f2fc23dea676ed77","entry":"my_encode","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/llm.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/llm.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"obj:dict/0/?","fixture_out_type":"memoryview","level_recorded_at":"2026-09-25T04:00:33.621019+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f2fc23dea676ed77"}},{"code_sha256":"d957a2e9f35bc763","code_sha256_prefix":"d957a2e9f35bc763","entry":"resize_to_max_pixels","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/module/directgen.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/module/directgen.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:dict/0/?, max_pixels:int/0/int","fixture_out_type":"dict","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d957a2e9f35bc763"}},{"code_sha256":"0892f960b112ef52","code_sha256_prefix":"0892f960b112ef52","entry":"strip_latex","repo":"LLMSELECTOR/LLMSELECTOR","repo_kind":"official","path":"llmselector/llmselector/compoundai/metric.py","file_url":"https://github.com/LLMSELECTOR/LLMSELECTOR/blob/HEAD/llmselector/llmselector/compoundai/metric.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"response:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"0892f960b112ef52"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0892f960b112ef52"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d54242c9f0c1f0c0e1396c96b44d00dacd795f27921cfdbc166ceaef0b27fb67","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}