{"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/conrft-a-reinforced-fine-tuning-method-for","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","arxiv_id":"2502.05450","date":"2025-02-08","proceeding":null,"authors":["Yuhui Chen","Shuai Tian","Shugao Liu","Yingting Zhou","Haoran Li","Dongbin Zhao"],"abstract":"Vision-Language-Action (VLA) models have shown substantial potential in real-world robotic manipulation. However, fine-tuning these models through supervised learning struggles to achieve robust performance due to limited, inconsistent demonstrations, especially in contact-rich environments. In this paper, we propose a reinforced fine-tuning approach for VLA models, named ConRFT, which consists of offline and online fine-tuning with a unified consistency-based training objective, to address these challenges. In the offline stage, our method integrates behavior cloning and Q-learning to effectively extract policy from a small set of demonstrations and stabilize value estimating. In the online stage, the VLA model is further fine-tuned via consistency policy, with human interventions to ensure safe exploration and high sample efficiency. We evaluate our approach on eight diverse real-world manipulation tasks. It achieves an average success rate of 96.3% within 45-90 minutes of online fine-tuning, outperforming prior supervised methods with a 144% improvement in success rate and 1.9x shorter episode length. This work highlights the potential of integrating reinforcement learning to enhance the performance of VLA models for real-world robotic applications. Videos and code are available at our project website https://cccedric.github.io/conrft/.","url_abs":"https://arxiv.org/abs/2502.05450v2","url_pdf":"https://arxiv.org/pdf/2502.05450v2.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":"conrft-a-reinforced-fine-tuning-method-for","repo_url":"https://github.com/cccedric/conrft","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"safe-exploration","task_name":"Safe Exploration"},{"task_slug":"vision-language-action","task_name":"Vision-Language-Action"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.05450","atlas_url":"https://app.syntology.ai/?focus=2502.05450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05450"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.05450"},"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":"2502.05450"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.05450\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2502.05450"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2502.05450\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2502.05450"},"call":"get_concepts_for_paper(arxiv_id=\"2502.05450\")"}],"by_repo":[{"repo":"cccedric/conrft","kind":"official","samples":5,"ran":5,"instrument":0,"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/2502.05450.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/2502.05450.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/cccedric/conrft","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":3,"ran":2},"n_samples":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"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":5,"ran":5,"n_ran_checked":5,"n_instrument":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":4,"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":4,"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":5,"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":"87d1bc442d93916d","code_sha256_prefix":"87d1bc442d93916d","entry":"cosine_beta_schedule","repo":"cccedric/conrft","repo_kind":"official","path":"serl_launcher/serl_launcher/networks/diffusion_nets.py","file_url":"https://github.com/cccedric/conrft/blob/HEAD/serl_launcher/serl_launcher/networks/diffusion_nets.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"timesteps:int/0/int, s:float/0/float","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"87d1bc442d93916d"},"code_page":"/code/cosine-beta-schedule","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Alescontrela/score_matching_rl, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"87d1bc442d93916d"}},{"code_sha256":"4e9a6a46c6aeee0b","code_sha256_prefix":"4e9a6a46c6aeee0b","entry":"ensemblize","repo":"cccedric/conrft","repo_kind":"official","path":"serl_launcher/serl_launcher/networks/actor_critic_nets.py","file_url":"https://github.com/cccedric/conrft/blob/HEAD/serl_launcher/serl_launcher/networks/actor_critic_nets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"cls:callable/0/?, num_qs:int/0/int, out_axes:int/0/int","fixture_out_type":"type","level_recorded_at":"2026-09-25T15:42:09.353852+00:00","code_page":"/code/ensemblize","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from zhouzypaul/wsrl, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"4e9a6a46c6aeee0b"}},{"code_sha256":"0cd44ae2231fcb3b","code_sha256_prefix":"0cd44ae2231fcb3b","entry":"linear_beta_schedule","repo":"cccedric/conrft","repo_kind":"official","path":"serl_launcher/serl_launcher/networks/diffusion_nets.py","file_url":"https://github.com/cccedric/conrft/blob/HEAD/serl_launcher/serl_launcher/networks/diffusion_nets.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"timesteps:int/0/int, beta_start:float/0/float, beta_end:float/0/float","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/linear-beta-schedule","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from diffusionyes/MaxEntDP, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"0cd44ae2231fcb3b"}},{"code_sha256":"c3ca7e8bfa98a6a6","code_sha256_prefix":"c3ca7e8bfa98a6a6","entry":"multiple_action_q_function","repo":"cccedric/conrft","repo_kind":"official","path":"serl_launcher/serl_launcher/networks/actor_critic_nets.py","file_url":"https://github.com/cccedric/conrft/blob/HEAD/serl_launcher/serl_launcher/networks/actor_critic_nets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"forward:callable/0/?","fixture_out_type":"function","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":"/code/multiple-action-q-function","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c3ca7e8bfa98a6a6"}},{"code_sha256":"539aaf559a17a19a","code_sha256_prefix":"539aaf559a17a19a","entry":"vp_beta_schedule","repo":"cccedric/conrft","repo_kind":"official","path":"serl_launcher/serl_launcher/networks/diffusion_nets.py","file_url":"https://github.com/cccedric/conrft/blob/HEAD/serl_launcher/serl_launcher/networks/diffusion_nets.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"timesteps:int/0/int","fixture_out_type":"ArrayImpl","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"539aaf559a17a19a"},"code_page":"/code/vp-beta-schedule","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Alescontrela/score_matching_rl, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"539aaf559a17a19a"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"df75fc395fb2811a03e752c4ae42748e17a1a96a2a8da1a92ce15741db899a8f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}