{"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/proactive-agent-shifting-llm-agents-from","title":"Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance","arxiv_id":"2410.12361","date":"2024-10-16","proceeding":null,"authors":["Yaxi Lu","Shenzhi Yang","Cheng Qian","Guirong Chen","Qinyu Luo","Yesai Wu","Huadong Wang","Xin Cong","Zhong Zhang","Yankai Lin","Weiwen Liu","Yasheng Wang","Zhiyuan Liu","Fangming Liu","Maosong Sun"],"abstract":"Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In this paper, we tackle the challenge of developing proactive agents capable of anticipating and initiating tasks without explicit human instructions. We propose a novel data-driven approach for this problem. Firstly, we collect real-world human activities to generate proactive task predictions. These predictions are then labeled by human annotators as either accepted or rejected. The labeled data is used to train a reward model that simulates human judgment and serves as an automatic evaluator of the proactiveness of LLM agents. Building on this, we develop a comprehensive data generation pipeline to create a diverse dataset, ProactiveBench, containing 6,790 events. Finally, we demonstrate that fine-tuning models with the proposed ProactiveBench can significantly elicit the proactiveness of LLM agents. Experimental results show that our fine-tuned model achieves an F1-Score of 66.47% in proactively offering assistance, outperforming all open-source and close-source models. These results highlight the potential of our method in creating more proactive and effective agent systems, paving the way for future advancements in human-agent collaboration.","url_abs":"https://arxiv.org/abs/2410.12361v3","url_pdf":"https://arxiv.org/pdf/2410.12361v3.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":"proactive-agent-shifting-llm-agents-from","repo_url":"https://github.com/thunlp/proactiveagent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"human-agent-collaboration","task_name":"Human Agent Collaboration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.12361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12361"}},"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/thunlp/proactiveagent","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":"6df273ea032c1eee","entry":"cut_messages","repo":"thunlp/proactiveagent","repo_kind":"official","path":"dataset/build_agent_trainset.py","file_url":"https://github.com/thunlp/proactiveagent/blob/HEAD/dataset/build_agent_trainset.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":"6df273ea032c1eee"}},{"code_sha256_prefix":"bbab44ae333b7271","entry":"extrat_pred","repo":"thunlp/proactiveagent","repo_kind":"official","path":"dataset/build_agent_trainset.py","file_url":"https://github.com/thunlp/proactiveagent/blob/HEAD/dataset/build_agent_trainset.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":"bbab44ae333b7271"}},{"code_sha256_prefix":"288e12deebad1396","entry":"format_message","repo":"thunlp/proactiveagent","repo_kind":"official","path":"dataset/build_reward_trainset.py","file_url":"https://github.com/thunlp/proactiveagent/blob/HEAD/dataset/build_reward_trainset.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":"288e12deebad1396"}},{"code_sha256_prefix":"bb2fc5fcd8d68b23","entry":"format_reward_instruction","repo":"thunlp/proactiveagent","repo_kind":"official","path":"eval/reward_model_template.py","file_url":"https://github.com/thunlp/proactiveagent/blob/HEAD/eval/reward_model_template.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":"bb2fc5fcd8d68b23"}},{"code_sha256_prefix":"c0f2bb2f36f724f7","entry":"format_thought_check","repo":"thunlp/proactiveagent","repo_kind":"official","path":"dataset/build_reward_trainset.py","file_url":"https://github.com/thunlp/proactiveagent/blob/HEAD/dataset/build_reward_trainset.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":"c0f2bb2f36f724f7"}},{"code_sha256_prefix":"7b909dda991ae7cf","entry":"read_text_from_file","repo":"thunlp/proactiveagent","repo_kind":"official","path":"agent/agentmodule.py","file_url":"https://github.com/thunlp/proactiveagent/blob/HEAD/agent/agentmodule.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":"7b909dda991ae7cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}