{"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/autoact-automatic-agent-learning-from-scratch","title":"AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning","arxiv_id":"2401.05268","date":"2024-01-10","proceeding":null,"authors":["Shuofei Qiao","Ningyu Zhang","Runnan Fang","Yujie Luo","Wangchunshu Zhou","Yuchen Eleanor Jiang","Chengfei Lv","Huajun Chen"],"abstract":"Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly, non-reproducible data reliance and face the challenge of compelling a single model for multiple functions. To this end, we introduce AutoAct, an automatic agent learning framework for QA that does not rely on large-scale annotated data and synthetic planning trajectories from closed-source models (e.g., GPT-4). Given limited data with a tool library, AutoAct first automatically synthesizes planning trajectories without any assistance from humans or strong closed-source models. Then, AutoAct leverages a division-of-labor strategy to automatically differentiate based on the target task information and synthesized trajectories, producing a sub-agent group to complete the task. We conduct comprehensive experiments with different LLMs, which demonstrates that AutoAct yields better or parallel performance compared to various strong baselines. Further analysis demonstrates the effectiveness of the division-of-labor strategy, with the trajectory quality generated by AutoAct generally outperforming that of others. Code will be available at https://github.com/zjunlp/AutoAct.","url_abs":"https://arxiv.org/abs/2401.05268v4","url_pdf":"https://arxiv.org/pdf/2401.05268v4.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":"autoact-automatic-agent-learning-from-scratch","repo_url":"https://github.com/zjunlp/autoact","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.05268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05268"}},"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/autoact","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":"0e8a991beb04061c","entry":"action_parse","repo":"zjunlp/autoact","repo_kind":"official","path":"Self_Plan/Tool_Selection/tool_selected.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Plan/Tool_Selection/tool_selected.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":"0e8a991beb04061c"}},{"code_sha256_prefix":"f62e3ab05a2163b7","entry":"format_step","repo":"zjunlp/autoact","repo_kind":"official","path":"Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.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":"f62e3ab05a2163b7"}},{"code_sha256_prefix":"9454beee89209dff","entry":"fuzzy_parse_action","repo":"zjunlp/autoact","repo_kind":"official","path":"Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9454beee89209dff"}},{"code_sha256_prefix":"4bd871433e574ddb","entry":"get_data_hotpotqa","repo":"zjunlp/autoact","repo_kind":"official","path":"Self_Instruct/data_generation.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Instruct/data_generation.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":"4bd871433e574ddb"}},{"code_sha256_prefix":"3e94a0fbc524b71a","entry":"get_data_scienceqa","repo":"zjunlp/autoact","repo_kind":"official","path":"Self_Instruct/data_generation.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Instruct/data_generation.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":"3e94a0fbc524b71a"}},{"code_sha256_prefix":"5e625f38abc7d9bf","entry":"get_random_data","repo":"zjunlp/autoact","repo_kind":"official","path":"Self_Instruct/data_generation.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Instruct/data_generation.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":"5e625f38abc7d9bf"}},{"code_sha256_prefix":"9f8148d447f9ea0c","entry":"parse_action","repo":"zjunlp/autoact","repo_kind":"official","path":"Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f8148d447f9ea0c"}},{"code_sha256_prefix":"c663f2a61a3ffcdc","entry":"sorted_values","repo":"zjunlp/autoact","repo_kind":"official","path":"Self_Plan/Tool_Selection/selector.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Plan/Tool_Selection/selector.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":"c663f2a61a3ffcdc"}},{"code_sha256_prefix":"1155f620a414f703","entry":"load_and_process_dataset","repo":"zjunlp/autoact","repo_kind":"official","path":"Self_Plan/Train/train_lora.py","file_url":"https://github.com/zjunlp/autoact/blob/HEAD/Self_Plan/Train/train_lora.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":"1155f620a414f703"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}