{"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/advancing-llm-reasoning-generalists-with","title":"Advancing LLM Reasoning Generalists with Preference Trees","arxiv_id":"2404.02078","date":"2024-04-02","proceeding":null,"authors":["Lifan Yuan","Ganqu Cui","Hanbin Wang","Ning Ding","Xingyao Wang","Jia Deng","Boji Shan","Huimin Chen","Ruobing Xie","Yankai Lin","Zhenghao Liu","BoWen Zhou","Hao Peng","Zhiyuan Liu","Maosong Sun"],"abstract":"We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Finetuned from Mistral-7B and CodeLlama-70B, Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks covering mathematics, code generation, and logical reasoning problems. Notably, Eurus-70B beats GPT-3.5 Turbo in reasoning through a comprehensive benchmarking across 12 tests covering five tasks, and achieves a 33.3% pass@1 accuracy on LeetCode and 32.6% on TheoremQA, two challenging benchmarks, substantially outperforming existing open-source models by margins more than 13.3%. The strong performance of Eurus can be primarily attributed to UltraInteract, our newly-curated large-scale, high-quality alignment dataset specifically designed for complex reasoning tasks. UltraInteract can be used in both supervised fine-tuning and preference learning. For each instruction, it includes a preference tree consisting of (1) reasoning chains with diverse planning strategies in a unified format, (2) multi-turn interaction trajectories with the environment and the critique, and (3) pairwise data to facilitate preference learning. UltraInteract allows us to conduct an in-depth exploration of preference learning for reasoning tasks. Our investigation reveals that some well-established preference learning algorithms may be less suitable for reasoning tasks compared to their effectiveness in general conversations. Inspired by this, we derive a novel reward modeling objective which, together with UltraInteract, leads to a strong reward model.","url_abs":"https://arxiv.org/abs/2404.02078v1","url_pdf":"https://arxiv.org/pdf/2404.02078v1.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":"advancing-llm-reasoning-generalists-with","repo_url":"https://github.com/openbmb/eurus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2404.02078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02078"}},"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/openbmb/eurus","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":4,"ran_violates":1,"ran":7,"unverified":7},"by_repo_kind":{"official":{"samples":20,"ran":13,"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":"19f01570b0a18e2b","entry":"softmax","repo":"openbmb/eurus","repo_kind":"official","path":"eval/mmlu/evaluate_mmlu.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/mmlu/evaluate_mmlu.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"19f01570b0a18e2b"}},{"code_sha256_prefix":"e080db2eaa81fdb3","entry":"estimate_pass_at_k","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/evaluation.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/evaluation.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e080db2eaa81fdb3"}},{"code_sha256_prefix":"cd763eaf1ac287e7","entry":"format_example","repo":"openbmb/eurus","repo_kind":"official","path":"eval/mmlu/evaluate_mmlu.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/mmlu/evaluate_mmlu.py","link_basis":"harvester_set","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":"cd763eaf1ac287e7"}},{"code_sha256_prefix":"6ab745408cb8648b","entry":"format_subject","repo":"openbmb/eurus","repo_kind":"official","path":"eval/mmlu/evaluate_mmlu.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/mmlu/evaluate_mmlu.py","link_basis":"harvester_set","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":"6ab745408cb8648b"}},{"code_sha256_prefix":"20063c675d638a77","entry":"is_equiv","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/math_equivalence.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/math_equivalence.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20063c675d638a77"}},{"code_sha256_prefix":"855a4d8c22777aac","entry":"last_boxed_only","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/util.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/util.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":"855a4d8c22777aac"}},{"code_sha256_prefix":"0b14c648516c38a7","entry":"last_boxed_only_string","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/util.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b14c648516c38a7"}},{"code_sha256_prefix":"c9c1b6ac091b90be","entry":"make_signature","repo":"openbmb/eurus","repo_kind":"official","path":"eval/Coding/human_eval/evaluate_human_eval.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/Coding/human_eval/evaluate_human_eval.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":"c9c1b6ac091b90be"}},{"code_sha256_prefix":"3ba288bfab3230c3","entry":"match_code","repo":"openbmb/eurus","repo_kind":"official","path":"eval/Coding/leetcode/evaluate_leetcode.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/Coding/leetcode/evaluate_leetcode.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":"3ba288bfab3230c3"}},{"code_sha256_prefix":"7131520594af5fe7","entry":"normalize_answer","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/math_normalize.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/math_normalize.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":"7131520594af5fe7"}},{"code_sha256_prefix":"a50f6b473e8d7cde","entry":"postprocess_completion","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/python_interpreter.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/python_interpreter.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":"a50f6b473e8d7cde"}},{"code_sha256_prefix":"8bbda0feb872faf2","entry":"postprocess_completion_wrapper","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/python_interpreter.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/python_interpreter.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":"8bbda0feb872faf2"}},{"code_sha256_prefix":"2a1cf35aaf759bca","entry":"read_problems","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/data.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/data.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":"2a1cf35aaf759bca"}},{"code_sha256_prefix":"12d4fef547070f7c","entry":"check_correctness","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/execution.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/execution.py","link_basis":"plan_row","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":"12d4fef547070f7c"}},{"code_sha256_prefix":"bb175bff1060d928","entry":"handle_base","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/grader.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/grader.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":"bb175bff1060d928"}},{"code_sha256_prefix":"2a180d3156997924","entry":"is_digit","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/grader.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/grader.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":"2a180d3156997924"}},{"code_sha256_prefix":"960059cee2753e3f","entry":"normalize","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/grader.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/grader.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":"960059cee2753e3f"}},{"code_sha256_prefix":"0bbf876ced018c83","entry":"only_until_first_boxed_from_tokens","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/util.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/util.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":"0bbf876ced018c83"}},{"code_sha256_prefix":"c313975ff5860b89","entry":"postprocess_completions","repo":"openbmb/eurus","repo_kind":"official","path":"eval/utils/python_interpreter.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/utils/python_interpreter.py","link_basis":"first_harvest_node","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":"c313975ff5860b89"}},{"code_sha256_prefix":"776a712a353130e7","entry":"read_problems","repo":"openbmb/eurus","repo_kind":"official","path":"eval/Coding/leetcode/data.py","file_url":"https://github.com/openbmb/eurus/blob/HEAD/eval/Coding/leetcode/data.py","link_basis":"plan_row","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":"776a712a353130e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}