{"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/parallel-continuous-chain-of-thought-with","title":"Parallel Continuous Chain-of-Thought with Jacobi Iteration","arxiv_id":"2506.18582","date":"2025-06-23","proceeding":null,"authors":["HaoYi Wu","Zhihao Teng","Kewei Tu"],"abstract":"Continuous chain-of-thought has been shown to be effective in saving reasoning tokens for large language models. By reasoning with continuous latent thought tokens, continuous CoT is able to perform implicit reasoning in a compact manner. However, the sequential dependencies between latent thought tokens spoil parallel training, leading to long training time. In this paper, we propose Parallel Continuous Chain-of-Thought (PCCoT), which performs Jacobi iteration on the latent thought tokens, updating them iteratively in parallel instead of sequentially and thus improving both training and inference efficiency of continuous CoT. Experiments demonstrate that by choosing the proper number of iterations, we are able to achieve comparable or even better performance while saving nearly 50% of the training and inference time. Moreover, PCCoT shows better stability and robustness in the training process. Our code is available at https://github.com/whyNLP/PCCoT.","url_abs":"https://arxiv.org/abs/2506.18582v1","url_pdf":"https://arxiv.org/pdf/2506.18582v1.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":"parallel-continuous-chain-of-thought-with","repo_url":"https://github.com/whynlp/pccot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2506.18582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18582"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/whynlp/pccot","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/whyNLP/PCCoT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":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,"samples":[{"code_sha256_prefix":"f9f635be24d5338c","entry":"PCCoTGPT2Config","repo":"whyNLP/PCCoT","repo_kind":"official","path":"models/modeling_gpt2.py","file_url":"https://github.com/whyNLP/PCCoT/blob/HEAD/models/modeling_gpt2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9f635be24d5338c"}},{"code_sha256_prefix":"b8e9b7055d258c05","entry":"PCCoTGPT2LMHeadModel","repo":"whyNLP/PCCoT","repo_kind":"official","path":"models/modeling_gpt2.py","file_url":"https://github.com/whyNLP/PCCoT/blob/HEAD/models/modeling_gpt2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8e9b7055d258c05"}},{"code_sha256_prefix":"8adc7e1171c8565b","entry":"PCCoTGenerationMixin","repo":"whyNLP/PCCoT","repo_kind":"official","path":"models/modeling_gpt2.py","file_url":"https://github.com/whyNLP/PCCoT/blob/HEAD/models/modeling_gpt2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8adc7e1171c8565b"}},{"code_sha256_prefix":"bb54c07894825120","entry":"batch_tokenize_number","repo":"whynlp/pccot","repo_kind":"official","path":"models/data_processor.py","file_url":"https://github.com/whynlp/pccot/blob/HEAD/models/data_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb54c07894825120"}},{"code_sha256_prefix":"bc0c56498e066b0d","entry":"is_llama_tokenizer","repo":"whynlp/pccot","repo_kind":"official","path":"models/data_processor.py","file_url":"https://github.com/whynlp/pccot/blob/HEAD/models/data_processor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc0c56498e066b0d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}