{"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/automatic-curriculum-expert-iteration-for","title":"Automatic Curriculum Expert Iteration for Reliable LLM Reasoning","arxiv_id":"2410.07627","date":"2024-10-10","proceeding":null,"authors":["Zirui Zhao","Hanze Dong","Amrita Saha","Caiming Xiong","Doyen Sahoo"],"abstract":"Hallucinations (i.e., generating plausible but inaccurate content) and laziness (i.e. excessive refusals or defaulting to \"I don't know\") persist as major challenges in LLM reasoning. Current efforts to reduce hallucinations primarily focus on factual errors in knowledge-grounded tasks, often neglecting hallucinations related to faulty reasoning. Meanwhile, some approaches render LLMs overly conservative, limiting their problem-solving capabilities. To mitigate hallucination and laziness in reasoning tasks, we propose Automatic Curriculum Expert Iteration (Auto-CEI) to enhance LLM reasoning and align responses to the model's capabilities--assertively answering within its limits and declining when tasks exceed them. In our method, Expert Iteration explores the reasoning trajectories near the LLM policy, guiding incorrect paths back on track to reduce compounding errors and improve robustness; it also promotes appropriate \"I don't know\" responses after sufficient reasoning attempts. The curriculum automatically adjusts rewards, incentivizing extended reasoning before acknowledging incapability, thereby pushing the limits of LLM reasoning and aligning its behaviour with these limits. We compare Auto-CEI with various SOTA baselines across logical reasoning, mathematics, and planning tasks, where Auto-CEI achieves superior alignment by effectively balancing assertiveness and conservativeness. The code is available at https://github.com/SalesforceAIResearch/Auto-CEI .","url_abs":"https://arxiv.org/abs/2410.07627v2","url_pdf":"https://arxiv.org/pdf/2410.07627v2.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":"automatic-curriculum-expert-iteration-for","repo_url":"https://github.com/salesforceairesearch/auto-cei","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.07627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07627"}},"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/salesforceairesearch/auto-cei","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"8529d921bdf3f1aa","entry":"last_boxed_only_string","repo":"salesforceairesearch/auto-cei","repo_kind":"official","path":"data/MATH/data_pre.py","file_url":"https://github.com/salesforceairesearch/auto-cei/blob/HEAD/data/MATH/data_pre.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8529d921bdf3f1aa"}},{"code_sha256_prefix":"e904b8cb1bf04964","entry":"modify","repo":"salesforceairesearch/auto-cei","repo_kind":"official","path":"data/MATH/data_pre.py","file_url":"https://github.com/salesforceairesearch/auto-cei/blob/HEAD/data/MATH/data_pre.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e904b8cb1bf04964"}},{"code_sha256_prefix":"05ccbbbc214e3ed4","entry":"remove_boxed","repo":"salesforceairesearch/auto-cei","repo_kind":"official","path":"data/MATH/data_pre.py","file_url":"https://github.com/salesforceairesearch/auto-cei/blob/HEAD/data/MATH/data_pre.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"05ccbbbc214e3ed4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}