{"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/swissnyf-tool-grounded-llm-agents-for-black","title":"SwissNYF: Tool Grounded LLM Agents for Black Box Setting","arxiv_id":"2402.10051","date":"2024-02-15","proceeding":null,"authors":["Somnath Sendhil Kumar","Dhruv Jain","Eshaan Agarwal","Raunak Pandey"],"abstract":"While Large Language Models (LLMs) have demonstrated enhanced capabilities in function-calling, these advancements primarily rely on accessing the functions' responses. This methodology is practical for simpler APIs but faces scalability issues with irreversible APIs that significantly impact the system, such as a database deletion API. Similarly, processes requiring extensive time for each API call and those necessitating forward planning, like automated action pipelines, present complex challenges. Furthermore, scenarios often arise where a generalized approach is needed because algorithms lack direct access to the specific implementations of these functions or secrets to use them. Traditional tool planning methods are inadequate in these cases, compelling the need to operate within black-box environments. Unlike their performance in tool manipulation, LLMs excel in black-box tasks, such as program synthesis. Therefore, we harness the program synthesis capabilities of LLMs to strategize tool usage in black-box settings, ensuring solutions are verified prior to implementation. We introduce TOPGUN, an ingeniously crafted approach leveraging program synthesis for black box tool planning. Accompanied by SwissNYF, a comprehensive suite that integrates black-box algorithms for planning and verification tasks, addressing the aforementioned challenges and enhancing the versatility and effectiveness of LLMs in complex API interactions. The public code for SwissNYF is available at https://github.com/iclr-dummy-user/SwissNYF.","url_abs":"https://arxiv.org/abs/2402.10051v1","url_pdf":"https://arxiv.org/pdf/2402.10051v1.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":"swissnyf-tool-grounded-llm-agents-for-black","repo_url":"https://github.com/iclr-dummy-user/swissnyf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"program-synthesis","task_name":"Program Synthesis"},{"task_slug":"trajectory-planning","task_name":"Trajectory Planning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/trajectory-planning-on-toolbench","task":"Trajectory Planning","dataset":"ToolBench","model":"GPT4-TOPGUN","rank_in_archive_order":1,"of":3,"metrics":{"Win rate":"86.54"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.10051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10051"}},"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":"deterministic:regex_extraction","url":"https://github.com/iclr-dummy-user/SwissNYF","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iclr-dummy-user/swissnyf","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"1462953ea9a7df14","entry":"parse_output","repo":"iclr-dummy-user/swissnyf","repo_kind":"official","path":"swissnyf/pipeline/top_gun.py","file_url":"https://github.com/iclr-dummy-user/swissnyf/blob/HEAD/swissnyf/pipeline/top_gun.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1462953ea9a7df14"}},{"code_sha256_prefix":"5281118eac7e67c9","entry":"update_traverse_dict","repo":"iclr-dummy-user/swissnyf","repo_kind":"official","path":"swissnyf/pipeline/top_gun.py","file_url":"https://github.com/iclr-dummy-user/swissnyf/blob/HEAD/swissnyf/pipeline/top_gun.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5281118eac7e67c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}