{"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/agent-planning-with-world-knowledge-model","title":"Agent Planning with World Knowledge Model","arxiv_id":"2405.14205","date":"2024-05-23","proceeding":null,"authors":["Shuofei Qiao","Runnan Fang","Ningyu Zhang","Yuqi Zhu","Xiang Chen","Shumin Deng","Yong Jiang","Pengjun Xie","Fei Huang","Huajun Chen"],"abstract":"Recent endeavors towards directly using large language models (LLMs) as agent models to execute interactive planning tasks have shown commendable results. Despite their achievements, however, they still struggle with brainless trial-and-error in global planning and generating hallucinatory actions in local planning due to their poor understanding of the ``real'' physical world. Imitating humans' mental world knowledge model which provides global prior knowledge before the task and maintains local dynamic knowledge during the task, in this paper, we introduce parametric World Knowledge Model (WKM) to facilitate agent planning. Concretely, we steer the agent model to self-synthesize knowledge from both expert and sampled trajectories. Then we develop WKM, providing prior task knowledge to guide the global planning and dynamic state knowledge to assist the local planning. Experimental results on three complex real-world simulated datasets with three state-of-the-art open-source LLMs, Mistral-7B, Gemma-7B, and Llama-3-8B, demonstrate that our method can achieve superior performance compared to various strong baselines. Besides, we analyze to illustrate that our WKM can effectively alleviate the blind trial-and-error and hallucinatory action issues, providing strong support for the agent's understanding of the world. Other interesting findings include: 1) our instance-level task knowledge can generalize better to unseen tasks, 2) weak WKM can guide strong agent model planning, and 3) unified WKM training has promising potential for further development. The code is available at https://github.com/zjunlp/WKM.","url_abs":"https://arxiv.org/abs/2405.14205v4","url_pdf":"https://arxiv.org/pdf/2405.14205v4.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":"agent-planning-with-world-knowledge-model","repo_url":"https://github.com/zjunlp/wkm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"world-knowledge","task_name":"World Knowledge"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.14205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14205"}},"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/wkm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":"be13dc8dd2c68d94","entry":"find_icl_example","repo":"zjunlp/wkm","repo_kind":"official","path":"src/train_data_process.py","file_url":"https://github.com/zjunlp/wkm/blob/HEAD/src/train_data_process.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":"be13dc8dd2c68d94"}},{"code_sha256_prefix":"5f5e5611bb3ea296","entry":"guideline_filter","repo":"zjunlp/wkm","repo_kind":"official","path":"src/train_data_process.py","file_url":"https://github.com/zjunlp/wkm/blob/HEAD/src/train_data_process.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":"5f5e5611bb3ea296"}},{"code_sha256_prefix":"6c711d17b733aaa5","entry":"metadata_func","repo":"zjunlp/wkm","repo_kind":"official","path":"src/state_base_build.py","file_url":"https://github.com/zjunlp/wkm/blob/HEAD/src/state_base_build.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":"6c711d17b733aaa5"}},{"code_sha256_prefix":"2ff69200f10a0559","entry":"Chat_Model","repo":"zjunlp/wkm","repo_kind":"official","path":"src/utils/chat_model.py","file_url":"https://github.com/zjunlp/wkm/blob/HEAD/src/utils/chat_model.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":"2ff69200f10a0559"}},{"code_sha256_prefix":"eefaa52fc92c8f55","entry":"get_conv_template","repo":"zjunlp/wkm","repo_kind":"official","path":"src/eval/fastchat/conversation.py","file_url":"https://github.com/zjunlp/wkm/blob/HEAD/src/eval/fastchat/conversation.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":"eefaa52fc92c8f55"}},{"code_sha256_prefix":"d25158a6396364bb","entry":"process_wm","repo":"zjunlp/wkm","repo_kind":"official","path":"src/train_data_process.py","file_url":"https://github.com/zjunlp/wkm/blob/HEAD/src/train_data_process.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":"d25158a6396364bb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}