{"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/agentic-knowledgeable-self-awareness","title":"Agentic Knowledgeable Self-awareness","arxiv_id":"2504.03553","date":"2025-04-04","proceeding":null,"authors":["Shuofei Qiao","Zhisong Qiu","Baochang Ren","Xiaobin Wang","Xiangyuan Ru","Ningyu Zhang","Xiang Chen","Yong Jiang","Pengjun Xie","Fei Huang","Huajun Chen"],"abstract":"Large Language Models (LLMs) have achieved considerable performance across various agentic planning tasks. However, traditional agent planning approaches adopt a \"flood irrigation\" methodology that indiscriminately injects gold trajectories, external feedback, and domain knowledge into agent models. This practice overlooks the fundamental human cognitive principle of situational self-awareness during decision-making-the ability to dynamically assess situational demands and strategically employ resources during decision-making. We propose agentic knowledgeable self-awareness to address this gap, a novel paradigm enabling LLM-based agents to autonomously regulate knowledge utilization. Specifically, we propose KnowSelf, a data-centric approach that applies agents with knowledgeable self-awareness like humans. Concretely, we devise a heuristic situation judgement criterion to mark special tokens on the agent's self-explored trajectories for collecting training data. Through a two-stage training process, the agent model can switch between different situations by generating specific special tokens, achieving optimal planning effects with minimal costs. Our experiments demonstrate that KnowSelf can outperform various strong baselines on different tasks and models with minimal use of external knowledge. Code is available at https://github.com/zjunlp/KnowSelf.","url_abs":"https://arxiv.org/abs/2504.03553v2","url_pdf":"https://arxiv.org/pdf/2504.03553v2.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":"agentic-knowledgeable-self-awareness","repo_url":"https://github.com/zjunlp/knowself","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[{"method_slug":"adopt","method_name":"ADOPT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.03553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.03553"}},"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/zjunlp/knowself","reach":null}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":"a1b197616af86079","entry":"GemmaTemplator","repo":"zjunlp/knowself","repo_kind":"official","path":"train/train_stage1.py","file_url":"https://github.com/zjunlp/knowself/blob/HEAD/train/train_stage1.py","link_basis":"first_harvest_node","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":"a1b197616af86079"}},{"code_sha256_prefix":"167e22a9b15461c1","entry":"Llama3Templator","repo":"zjunlp/knowself","repo_kind":"official","path":"train/train_stage1.py","file_url":"https://github.com/zjunlp/knowself/blob/HEAD/train/train_stage1.py","link_basis":"first_harvest_node","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":"167e22a9b15461c1"}},{"code_sha256_prefix":"8baed8907582a4a3","entry":"Qwen2Templator","repo":"zjunlp/knowself","repo_kind":"official","path":"train/train_stage1.py","file_url":"https://github.com/zjunlp/knowself/blob/HEAD/train/train_stage1.py","link_basis":"first_harvest_node","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":"8baed8907582a4a3"}},{"code_sha256_prefix":"091e063b8c292191","entry":"Templator","repo":"zjunlp/knowself","repo_kind":"official","path":"train/train_stage1.py","file_url":"https://github.com/zjunlp/knowself/blob/HEAD/train/train_stage1.py","link_basis":"first_harvest_node","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":"091e063b8c292191"}},{"code_sha256_prefix":"413afba62a8952fc","entry":"encode_with_messages_format","repo":"zjunlp/knowself","repo_kind":"official","path":"train/train_stage1.py","file_url":"https://github.com/zjunlp/knowself/blob/HEAD/train/train_stage1.py","link_basis":"first_harvest_node","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":"413afba62a8952fc"}},{"code_sha256_prefix":"5bbf3791e217df26","entry":"main","repo":"zjunlp/knowself","repo_kind":"official","path":"train/train_stage1.py","file_url":"https://github.com/zjunlp/knowself/blob/HEAD/train/train_stage1.py","link_basis":"first_harvest_node","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":"5bbf3791e217df26"}},{"code_sha256_prefix":"b1cc0d38e387f876","entry":"parse_args","repo":"zjunlp/knowself","repo_kind":"official","path":"train/train_stage1.py","file_url":"https://github.com/zjunlp/knowself/blob/HEAD/train/train_stage1.py","link_basis":"first_harvest_node","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":"b1cc0d38e387f876"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}