{"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/trajectory-balance-with-asynchrony-decoupling","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","arxiv_id":"2503.18929","date":"2025-03-24","proceeding":null,"authors":["Brian R. Bartoldson","Siddarth Venkatraman","James Diffenderfer","Moksh Jain","Tal Ben-Nun","Seanie Lee","Minsu Kim","Johan Obando-Ceron","Yoshua Bengio","Bhavya Kailkhura"],"abstract":"Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, existing on-policy algorithms used for post-training are inherently incompatible with the use of experience replay buffers, which can be populated scalably by distributed off-policy actors to enhance exploration as compute increases. We propose efficiently obtaining this benefit of replay buffers via Trajectory Balance with Asynchrony (TBA), a massively scalable LLM RL system. In contrast to existing approaches, TBA uses a larger fraction of compute on search, constantly generating off-policy data for a central replay buffer. A training node simultaneously samples data from this buffer based on reward or recency to update the policy using Trajectory Balance (TB), a diversity-seeking RL objective introduced for GFlowNets. TBA offers three key advantages: (1) decoupled training and search, speeding up training wall-clock time by 4x or more; (2) improved diversity through large-scale off-policy sampling; and (3) scalable search for sparse reward settings. On mathematical reasoning, preference-tuning, and automated red-teaming (diverse and representative post-training tasks), TBA produces speed and performance improvements over strong baselines.","url_abs":"https://arxiv.org/abs/2503.18929v1","url_pdf":"https://arxiv.org/pdf/2503.18929v1.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":"trajectory-balance-with-asynchrony-decoupling","repo_url":"https://github.com/bbartoldson/TBA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"red-teaming","task_name":"Red Teaming"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"experience-replay","method_name":"Experience Replay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.18929","atlas_url":"https://app.syntology.ai/?focus=2503.18929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18929"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2503.18929"},"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":"2503.18929"},"call":"get_harvested_code_for_paper(arxiv_id=\"2503.18929\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2503.18929"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2503.18929\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2503.18929"},"call":"get_concepts_for_paper(arxiv_id=\"2503.18929\")"}],"by_repo":[{"repo":"bbartoldson/TBA","kind":"listed","samples":10,"ran":7,"instrument":0,"unverified":3}],"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/2503.18929.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/2503.18929.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":"deterministic:regex_extraction","url":"https://github.com/bbartoldson/TBA","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"unverified":3},"n_samples":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"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":{"listed":{"samples":10,"ran":7,"n_ran_checked":7,"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":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":7,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","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":"d0b3a48ae72ccfc4","code_sha256_prefix":"d0b3a48ae72ccfc4","entry":"build_example_dataloader","repo":"bbartoldson/TBA","repo_kind":"listed","path":"src/dist_data_utils.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/src/dist_data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"dataset:MinimalDataset/0/?, tokenizer:callable/0/?, batch_size:int/0/int","fixture_out_type":"DataLoader","level_recorded_at":"2026-09-24T23:57:41.519889+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":"d0b3a48ae72ccfc4"}},{"code_sha256":"a26a4bc2f82b9ec2","code_sha256_prefix":"a26a4bc2f82b9ec2","entry":"extract_prediction","repo":"bbartoldson/TBA","repo_kind":"listed","path":"src/gsm8k_utils.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/src/gsm8k_utils.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":"float","level_recorded_at":"2026-09-24T23:57:41.519889+00:00","retrieve_with":{"tool":"get_code","code_sha256":"a26a4bc2f82b9ec2"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a26a4bc2f82b9ec2"}},{"code_sha256":"150dea51d807fbaa","code_sha256_prefix":"150dea51d807fbaa","entry":"format_and_tokenize","repo":"bbartoldson/TBA","repo_kind":"listed","path":"src/gsm8k_utils.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/src/gsm8k_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"example:dict/0/?, tokenizer:callable/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-25T00:28:05.031210+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":"150dea51d807fbaa"}},{"code_sha256":"d70961db4cf293ba","code_sha256_prefix":"d70961db4cf293ba","entry":"ignore_prompt_labels","repo":"bbartoldson/TBA","repo_kind":"listed","path":"src/kl.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/src/kl.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"batch:dict/0/?, response_token_ids:Tensor/1/int, ignore_index:int/0/int, tokenizer:NoneType/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-24T23:57:41.519889+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":"d70961db4cf293ba"}},{"code_sha256":"5503c179cc4b29b0","code_sha256_prefix":"5503c179cc4b29b0","entry":"next_free_port","repo":"bbartoldson/TBA","repo_kind":"listed","path":"src/dist_utils.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/src/dist_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"port:int/0/int, max_port:int/0/int","fixture_out_type":"int","level_recorded_at":"2026-09-25T01:58:58.792130+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5503c179cc4b29b0"},"code_page":"/code/next-free-port","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5503c179cc4b29b0"}},{"code_sha256":"cd83783cc6325cf1","code_sha256_prefix":"cd83783cc6325cf1","entry":"parse_number","repo":"bbartoldson/TBA","repo_kind":"listed","path":"src/gsm8k_utils.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/src/gsm8k_utils.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":"float","level_recorded_at":"2026-09-24T23:57:41.519889+00:00","retrieve_with":{"tool":"get_code","code_sha256":"cd83783cc6325cf1"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cd83783cc6325cf1"}},{"code_sha256":"9860770ecc9b4ebe","code_sha256_prefix":"9860770ecc9b4ebe","entry":"split_dataset_indices","repo":"bbartoldson/TBA","repo_kind":"listed","path":"src/dist_data_utils.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/src/dist_data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"total_size:int/0/int, K:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","retrieve_with":{"tool":"get_code","code_sha256":"9860770ecc9b4ebe"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9860770ecc9b4ebe"}},{"code_sha256":"2ed37256b49d8561","code_sha256_prefix":"2ed37256b49d8561","entry":"example_prepare_dataset","repo":"bbartoldson/TBA","repo_kind":"listed","path":"src/dist_data_utils.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/src/dist_data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2ed37256b49d8561"}},{"code_sha256":"a2e246bb45f45630","code_sha256_prefix":"a2e246bb45f45630","entry":"prepare_dataset","repo":"bbartoldson/TBA","repo_kind":"listed","path":"tba_tldr.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/tba_tldr.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/prepare-dataset","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a2e246bb45f45630"}},{"code_sha256":"e0030346eb43e3a2","code_sha256_prefix":"e0030346eb43e3a2","entry":"prepare_deepspeed","repo":"bbartoldson/TBA","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/bbartoldson/TBA/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e0030346eb43e3a2"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c7e7b7706574889fcc161f5539062fb2b7ae7959d465f516be39daea6615819b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}