{"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/soundmind-rl-incentivized-logic-reasoning-for","title":"SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models","arxiv_id":"2506.12935","date":"2025-06-15","proceeding":null,"authors":["Xingjian Diao","Chunhui Zhang","Keyi Kong","Weiyi Wu","Chiyu Ma","Zhongyu Ouyang","Peijun Qing","Soroush Vosoughi","Jiang Gui"],"abstract":"While large language models have shown reasoning capabilities, their application to the audio modality, particularly in large audio-language models (ALMs), remains significantly underdeveloped. Addressing this gap requires a systematic approach, involving a capable base model, high-quality reasoning-oriented audio data, and effective training algorithms. In this study, we present a comprehensive solution: we introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotated samples specifically designed for complex reasoning tasks. Building on this resource, we propose SoundMind, a rule-based reinforcement learning (RL) algorithm tailored to endow ALMs with deep bimodal reasoning abilities. By training Qwen2.5-Omni-7B on the ALR dataset using SoundMind, our approach achieves state-of-the-art performance in audio logical reasoning. This work highlights the impact of combining high-quality, reasoning-focused datasets with specialized RL techniques, advancing the frontier of auditory intelligence in language models. Our code and the proposed dataset are available at https://github.com/xid32/SoundMind.","url_abs":"https://arxiv.org/abs/2506.12935v1","url_pdf":"https://arxiv.org/pdf/2506.12935v1.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":"soundmind-rl-incentivized-logic-reasoning-for","repo_url":"https://github.com/xid32/soundmind","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.12935","atlas_url":"https://app.syntology.ai/?focus=2506.12935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.12935"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/xid32/SoundMind","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":3,"ran_violates":1,"ran_fixture":1,"unverified":7},"by_repo_kind":{"official":{"samples":16,"ran":9,"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":"f220595adfc5e83c","entry":"compute_ce_dpo_loss_rm","repo":"xid32/SoundMind","repo_kind":"official","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/prime/prime_core_algos.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f220595adfc5e83c"}},{"code_sha256_prefix":"4d91e4383716e42c","entry":"compute_detach_dpo_loss_rm","repo":"xid32/SoundMind","repo_kind":"official","path":"recipe/prime/prime_core_algos.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/prime/prime_core_algos.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d91e4383716e42c"}},{"code_sha256_prefix":"f19825983a523003","entry":"compute_online_dpo_loss","repo":"xid32/SoundMind","repo_kind":"official","path":"recipe/spin/core_algos.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/spin/core_algos.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f19825983a523003"}},{"code_sha256_prefix":"7a988deb09f43a64","entry":"compute_onlinedpo_pref","repo":"xid32/SoundMind","repo_kind":"official","path":"recipe/spin/core_algos.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/spin/core_algos.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a988deb09f43a64"}},{"code_sha256_prefix":"757d109d90121142","entry":"get_kl_controller","repo":"xid32/SoundMind","repo_kind":"official","path":"recipe/spin/core_algos.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/spin/core_algos.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"757d109d90121142"}},{"code_sha256_prefix":"735e93af30b15fa9","entry":"is_ipv4","repo":"xid32/SoundMind","repo_kind":"official","path":"verl/utils/net_utils.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/utils/net_utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"735e93af30b15fa9"}},{"code_sha256_prefix":"c30b2a96103abd2c","entry":"reward_func","repo":"xid32/SoundMind","repo_kind":"official","path":"recipe/r1/reward_score.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/r1/reward_score.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c30b2a96103abd2c"}},{"code_sha256_prefix":"21331a58f93375e4","entry":"union_tensor_dict","repo":"xid32/SoundMind","repo_kind":"official","path":"verl/protocol.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/protocol.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"code_sha256_prefix":"25f0ea3f460f6ce1","entry":"unpad_dataproto","repo":"xid32/SoundMind","repo_kind":"official","path":"verl/protocol.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/protocol.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"25f0ea3f460f6ce1"}},{"code_sha256_prefix":"b6a2a67dab81f497","entry":"get_custom_reward_fn","repo":"xid32/SoundMind","repo_kind":"official","path":"recipe/dapo/main_dapo.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/dapo/main_dapo.py","link_basis":"harvester_set","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":"b6a2a67dab81f497"}},{"code_sha256_prefix":"5c059b45527bdff7","entry":"get_generation_config","repo":"xid32/SoundMind","repo_kind":"official","path":"verl/utils/model.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/utils/model.py","link_basis":"harvester_set","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":"5c059b45527bdff7"}},{"code_sha256_prefix":"0a5b4c20bc4ff94b","entry":"get_huggingface_actor_config","repo":"xid32/SoundMind","repo_kind":"official","path":"verl/utils/model.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/utils/model.py","link_basis":"harvester_set","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":"0a5b4c20bc4ff94b"}},{"code_sha256_prefix":"acf240079d434746","entry":"get_weight_loader","repo":"xid32/SoundMind","repo_kind":"official","path":"verl/models/weight_loader_registry.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/models/weight_loader_registry.py","link_basis":"harvester_set","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":"acf240079d434746"}},{"code_sha256_prefix":"aa51429ab4c58a74","entry":"get_weight_saver","repo":"xid32/SoundMind","repo_kind":"official","path":"verl/models/weight_loader_registry.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/models/weight_loader_registry.py","link_basis":"harvester_set","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":"aa51429ab4c58a74"}},{"code_sha256_prefix":"705afe175ad8e404","entry":"is_ipv6","repo":"xid32/SoundMind","repo_kind":"official","path":"verl/utils/net_utils.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/utils/net_utils.py","link_basis":"harvester_set","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":"705afe175ad8e404"}},{"code_sha256_prefix":"3b15e2ac7497c441","entry":"squeeze","repo":"xid32/SoundMind","repo_kind":"official","path":"verl/utils/model.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/verl/utils/model.py","link_basis":"harvester_set","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":"3b15e2ac7497c441"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}