{"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/an-open-source-software-toolkit-benchmark","title":"An Open-Source Software Toolkit & Benchmark Suite for the Evaluation and Adaptation of Multimodal Action Models","arxiv_id":"2506.09172","date":"2025-06-10","proceeding":null,"authors":["Pranav Guruprasad","Yangyue Wang","Sudipta Chowdhury","Jaewoo Song","Harshvardhan Sikka"],"abstract":"Recent innovations in multimodal action models represent a promising direction for developing general-purpose agentic systems, combining visual understanding, language comprehension, and action generation. We introduce MultiNet - a novel, fully open-source benchmark and surrounding software ecosystem designed to rigorously evaluate and adapt models across vision, language, and action domains. We establish standardized evaluation protocols for assessing vision-language models (VLMs) and vision-language-action models (VLAs), and provide open source software to download relevant data, models, and evaluations. Additionally, we provide a composite dataset with over 1.3 trillion tokens of image captioning, visual question answering, commonsense reasoning, robotic control, digital game-play, simulated locomotion/manipulation, and many more tasks. The MultiNet benchmark, framework, toolkit, and evaluation harness have been used in downstream research on the limitations of VLA generalization.","url_abs":"https://arxiv.org/abs/2506.09172v2","url_pdf":"https://arxiv.org/pdf/2506.09172v2.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":[],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"vision-language-action","task_name":"Vision-Language-Action"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.09172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09172"}},"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/ManifoldRG/MultiNet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"found_in_text":{"samples":10,"ran":0,"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":"8d58ac5b83569839","entry":"calculate_tp_fp_fn_counts","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"src/eval_utils.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/src/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8d58ac5b83569839"}},{"code_sha256_prefix":"9d33e334f0bb815c","entry":"format_instruction_prompt","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"definitions/openx_prompt.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/definitions/openx_prompt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9d33e334f0bb815c"}},{"code_sha256_prefix":"74d7ba558cf2673d","entry":"format_instruction_prompt","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"definitions/overcooked_prompt.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/definitions/overcooked_prompt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74d7ba558cf2673d"}},{"code_sha256_prefix":"c5fbf297af9cbd2a","entry":"format_instruction_prompt","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"definitions/procgen_prompt.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/definitions/procgen_prompt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c5fbf297af9cbd2a"}},{"code_sha256_prefix":"3123b8636cc08b8c","entry":"get_exact_match_rate","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"src/eval_utils.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/src/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3123b8636cc08b8c"}},{"code_sha256_prefix":"6df77a9bf8f4ff59","entry":"get_micro_precision_from_counts","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"src/eval_utils.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/src/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6df77a9bf8f4ff59"}},{"code_sha256_prefix":"19aec48ebc7f795d","entry":"jat","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"src/control_translation/centralized_translation.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/src/control_translation/centralized_translation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"19aec48ebc7f795d"}},{"code_sha256_prefix":"bc45d0ea835b7f1a","entry":"rlu","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"src/control_translation/centralized_translation.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/src/control_translation/centralized_translation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc45d0ea835b7f1a"}},{"code_sha256_prefix":"f7ced7f084753a05","entry":"shard_and_save","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"src/centralized_downloader.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/src/centralized_downloader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f7ced7f084753a05"}},{"code_sha256_prefix":"6002cd57abec4595","entry":"torchrlds","repo":"ManifoldRG/MultiNet","repo_kind":"found_in_text","path":"src/control_translation/centralized_translation.py","file_url":"https://github.com/ManifoldRG/MultiNet/blob/HEAD/src/control_translation/centralized_translation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6002cd57abec4595"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}