{"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/think-on-your-feet-adaptive-thinking-via","title":"Adaptive Thinking via Mode Policy Optimization for Social Language Agents","arxiv_id":"2505.02156","date":"2025-05-04","proceeding":null,"authors":["Minzheng Wang","Yongbin Li","Haobo Wang","Xinghua Zhang","Nan Xu","Bingli Wu","Fei Huang","Haiyang Yu","Wenji Mao"],"abstract":"Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current studies. Existing methods either lack this kind of reasoning capability or enforce Long Chain-of-Thought reasoning uniformly across all scenarios, resulting in excessive token usage and inflexible social simulation. To address this, we propose an $\\textbf{A}$daptive $\\textbf{M}$ode $\\textbf{L}$earning ($\\textbf{AML}$) framework in this paper, aiming to improve the adaptive thinking ability of language agents in dynamic social interactions. To this end, we first identify hierarchical thinking modes ranging from intuitive response to deep deliberation based on the cognitive control theory. We then develop the $\\textbf{A}$daptive $\\textbf{M}$ode $\\textbf{P}$olicy $\\textbf{O}$ptimization ($\\textbf{AMPO}$) algorithm to optimize the context-aware mode switching and reasoning. Our framework advances existing research in three key aspects: (1) Multi-granular thinking mode design, (2) Context-aware mode switching across social interaction, and (3) Token-efficient reasoning via depth-adaptive processing. Extensive experiments on social intelligence benchmarks verify that AML achieves 15.6% higher task performance than GPT-4o. Notably, our AMPO outperforms GRPO by 7.0% with 32.8% shorter reasoning chains, demonstrating the advantage of adaptive thinking mode selection and optimization mechanism in AMPO over GRPO's fixed-depth solution.","url_abs":"https://arxiv.org/abs/2505.02156v3","url_pdf":"https://arxiv.org/pdf/2505.02156v3.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":"think-on-your-feet-adaptive-thinking-via","repo_url":"https://github.com/MozerWang/AMPO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.02156","atlas_url":"https://app.syntology.ai/?focus=2505.02156","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02156"}},"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/MozerWang/AMPO","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"e10605fc9d184927","entry":"compute_ampo_outcome_advantage","repo":"MozerWang/AMPO","repo_kind":"official","path":"RL/verl/trainer/ppo/core_algos.py","file_url":"https://github.com/MozerWang/AMPO/blob/HEAD/RL/verl/trainer/ppo/core_algos.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":"e10605fc9d184927"}},{"code_sha256_prefix":"d376da2e6702c075","entry":"compute_mode_adv","repo":"MozerWang/AMPO","repo_kind":"official","path":"RL/verl/trainer/ppo/core_algos.py","file_url":"https://github.com/MozerWang/AMPO/blob/HEAD/RL/verl/trainer/ppo/core_algos.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":"d376da2e6702c075"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}