{"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/tomap-training-opponent-aware-llm-persuaders","title":"ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind","arxiv_id":"2505.22961","date":"2025-05-29","proceeding":null,"authors":["Peixuan Han","Zijia Liu","Jiaxuan You"],"abstract":"Large language models (LLMs) have shown promising potential in persuasion, but existing works on training LLM persuaders are still preliminary. Notably, while humans are skilled in modeling their opponent's thoughts and opinions proactively and dynamically, current LLMs struggle with such Theory of Mind (ToM) reasoning, resulting in limited diversity and opponent awareness. To address this limitation, we introduce Theory of Mind Augmented Persuader (ToMAP), a novel approach for building more flexible persuader agents by incorporating two theory of mind modules that enhance the persuader's awareness and analysis of the opponent's mental state. Specifically, we begin by prompting the persuader to consider possible objections to the target central claim, and then use a text encoder paired with a trained MLP classifier to predict the opponent's current stance on these counterclaims. Our carefully designed reinforcement learning schema enables the persuader learns how to analyze opponent-related information and utilize it to generate more effective arguments. Experiments show that the ToMAP persuader, while containing only 3B parameters, outperforms much larger baselines, like GPT-4o, with a relative gain of 39.4% across multiple persuadee models and diverse corpora. Notably, ToMAP exhibits complex reasoning chains and reduced repetition during training, which leads to more diverse and effective arguments. The opponent-aware feature of ToMAP also makes it suitable for long conversations and enables it to employ more logical and opponent-aware strategies. These results underscore our method's effectiveness and highlight its potential for developing more persuasive language agents. Code is available at: https://github.com/ulab-uiuc/ToMAP.","url_abs":"https://arxiv.org/abs/2505.22961v1","url_pdf":"https://arxiv.org/pdf/2505.22961v1.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":"tomap-training-opponent-aware-llm-persuaders","repo_url":"https://github.com/ulab-uiuc/tomap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.22961","atlas_url":"https://app.syntology.ai/?focus=2505.22961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.22961"}},"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/ulab-uiuc/ToMAP","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"ran_fixture":1,"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":10,"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":"360c671d6041ba3b","entry":"create_huggingface_actor","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/utils/model.py","file_url":"https://github.com/ulab-uiuc/ToMAP/blob/HEAD/verl/utils/model.py","link_basis":"harvester_set","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":"360c671d6041ba3b"}},{"code_sha256_prefix":"21331a58f93375e4","entry":"union_tensor_dict","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/protocol.py","file_url":"https://github.com/ulab-uiuc/ToMAP/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"code_sha256_prefix":"25f0ea3f460f6ce1","entry":"unpad_dataproto","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/protocol.py","file_url":"https://github.com/ulab-uiuc/ToMAP/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"25f0ea3f460f6ce1"}},{"code_sha256_prefix":"b7f13422453815ee","entry":"external_batch_inference","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/llm_agent/batch_inference.py","file_url":"https://github.com/ulab-uiuc/ToMAP/blob/HEAD/verl/llm_agent/batch_inference.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":"b7f13422453815ee"}},{"code_sha256_prefix":"4a1bf7c49ac2d0c9","entry":"extract_answer","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/env_feedback/argument_graph.py","file_url":"https://github.com/ulab-uiuc/ToMAP/blob/HEAD/verl/env_feedback/argument_graph.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":"4a1bf7c49ac2d0c9"}},{"code_sha256_prefix":"0c6b52668a53023a","entry":"format_turns","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/env_feedback/argument_graph.py","file_url":"https://github.com/ulab-uiuc/ToMAP/blob/HEAD/verl/env_feedback/argument_graph.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":"0c6b52668a53023a"}},{"code_sha256_prefix":"19472d4343d0a082","entry":"get_huggingface_actor_config","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/utils/model.py","file_url":"https://github.com/ulab-uiuc/ToMAP/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"19472d4343d0a082"}},{"code_sha256_prefix":"a8c0b5b7b7144100","entry":"get_score","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/env_feedback/argument_graph.py","file_url":"https://github.com/ulab-uiuc/ToMAP/blob/HEAD/verl/env_feedback/argument_graph.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":"a8c0b5b7b7144100"}},{"code_sha256_prefix":"919cf310ad4c189a","entry":"get_weight_loader","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/models/weight_loader_registry.py","file_url":"https://github.com/ulab-uiuc/ToMAP/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"919cf310ad4c189a"}},{"code_sha256_prefix":"3b15e2ac7497c441","entry":"squeeze","repo":"ulab-uiuc/ToMAP","repo_kind":"official","path":"verl/utils/model.py","file_url":"https://github.com/ulab-uiuc/ToMAP/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b15e2ac7497c441"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}