{"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/beyond-autoregression-discrete-diffusion-for","title":"Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning","arxiv_id":"2410.14157","date":"2024-10-18","proceeding":null,"authors":["Jiacheng Ye","Jiahui Gao","Shansan Gong","Lin Zheng","Xin Jiang","Zhenguo Li","Lingpeng Kong"],"abstract":"Autoregressive language models, despite their impressive capabilities, struggle with complex reasoning and long-term planning tasks. We introduce discrete diffusion models as a novel solution to these challenges. Through the lens of subgoal imbalance, we demonstrate how diffusion models effectively learn difficult subgoals that elude autoregressive approaches. We propose Multi-granularity Diffusion Modeling (MDM), which prioritizes subgoals based on difficulty during learning. On complex tasks like Countdown, Sudoku, and Boolean Satisfiability Problems, MDM significantly outperforms autoregressive models without using search techniques. For instance, MDM achieves 91.5\\% and 100\\% accuracy on Countdown and Sudoku, respectively, compared to 45.8\\% and 20.7\\% for autoregressive models. Our work highlights the potential of diffusion-based approaches in advancing AI capabilities for sophisticated language understanding and problem-solving tasks.","url_abs":"https://arxiv.org/abs/2410.14157v1","url_pdf":"https://arxiv.org/pdf/2410.14157v1.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":"beyond-autoregression-discrete-diffusion-for","repo_url":"https://github.com/HKUNLP/diffusion-vs-ar","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.14157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14157"}},"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/HKUNLP/diffusion-vs-ar","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"c9e23707f64ef795","entry":"count_parameters","repo":"HKUNLP/diffusion-vs-ar","repo_kind":"official","path":"src/llmtuner/extras/misc.py","file_url":"https://github.com/HKUNLP/diffusion-vs-ar/blob/HEAD/src/llmtuner/extras/misc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c9e23707f64ef795"}},{"code_sha256_prefix":"56faa444d1b260c6","entry":"get_logger","repo":"HKUNLP/diffusion-vs-ar","repo_kind":"official","path":"src/llmtuner/extras/logging.py","file_url":"https://github.com/HKUNLP/diffusion-vs-ar/blob/HEAD/src/llmtuner/extras/logging.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56faa444d1b260c6"}},{"code_sha256_prefix":"a9e798cf22bd399b","entry":"infer_optim_dtype","repo":"HKUNLP/diffusion-vs-ar","repo_kind":"official","path":"src/llmtuner/extras/misc.py","file_url":"https://github.com/HKUNLP/diffusion-vs-ar/blob/HEAD/src/llmtuner/extras/misc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9e798cf22bd399b"}},{"code_sha256_prefix":"f92a36628049ade8","entry":"pad_sequence","repo":"HKUNLP/diffusion-vs-ar","repo_kind":"official","path":"src/llmtuner/dsets/preprocess.py","file_url":"https://github.com/HKUNLP/diffusion-vs-ar/blob/HEAD/src/llmtuner/dsets/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f92a36628049ade8"}},{"code_sha256_prefix":"70c7f6d657ef0a9e","entry":"smooth","repo":"HKUNLP/diffusion-vs-ar","repo_kind":"official","path":"src/llmtuner/extras/ploting.py","file_url":"https://github.com/HKUNLP/diffusion-vs-ar/blob/HEAD/src/llmtuner/extras/ploting.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"70c7f6d657ef0a9e"}},{"code_sha256_prefix":"1c0a502523d29b60","entry":"split_dataset","repo":"HKUNLP/diffusion-vs-ar","repo_kind":"official","path":"src/llmtuner/dsets/utils.py","file_url":"https://github.com/HKUNLP/diffusion-vs-ar/blob/HEAD/src/llmtuner/dsets/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1c0a502523d29b60"}},{"code_sha256_prefix":"7aba54878bdf4a47","entry":"dispatch_model","repo":"HKUNLP/diffusion-vs-ar","repo_kind":"official","path":"src/llmtuner/extras/misc.py","file_url":"https://github.com/HKUNLP/diffusion-vs-ar/blob/HEAD/src/llmtuner/extras/misc.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":"7aba54878bdf4a47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}