{"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/swiftsage-a-generative-agent-with-fast-and-1","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","arxiv_id":"2305.17390","date":"2023-05-27","proceeding":"NeurIPS 2023 11","authors":["Bill Yuchen Lin","Yicheng Fu","Karina Yang","Faeze Brahman","Shiyu Huang","Chandra Bhagavatula","Prithviraj Ammanabrolu","Yejin Choi","Xiang Ren"],"abstract":"We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. SwiftSage integrates the strengths of behavior cloning and prompting large language models (LLMs) to enhance task completion performance. The framework comprises two primary modules: the Swift module, representing fast and intuitive thinking, and the Sage module, emulating deliberate thought processes. The Swift module is a small encoder-decoder LM fine-tuned on the oracle agent's action trajectories, while the Sage module employs LLMs such as GPT-4 for subgoal planning and grounding. We develop a heuristic method to harmoniously integrate the two modules, resulting in a more efficient and robust problem-solving process. In 30 tasks from the ScienceWorld benchmark, SwiftSage significantly outperforms other methods such as SayCan, ReAct, and Reflexion, demonstrating its effectiveness in solving complex interactive tasks.","url_abs":"https://arxiv.org/abs/2305.17390v2","url_pdf":"https://arxiv.org/pdf/2305.17390v2.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":"swiftsage-a-generative-agent-with-fast-and-1","repo_url":"https://github.com/re-align/just-eval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"swiftsage-a-generative-agent-with-fast-and-1","repo_url":"https://github.com/yuchenlin/swiftsage","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.17390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17390"}},"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/yuchenlin/swiftsage","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/re-align/just-eval","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"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":"1ceae8a4420766c6","entry":"fix_inner_quotes","repo":"re-align/just-eval","repo_kind":"listed","path":"just_eval/utils.py","file_url":"https://github.com/re-align/just-eval/blob/HEAD/just_eval/utils.py","link_basis":"harvester_set","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":"1ceae8a4420766c6"}},{"code_sha256_prefix":"0237f0380d5bf897","entry":"gpt_eval","repo":"re-align/just-eval","repo_kind":"listed","path":"just_eval/evaluate.py","file_url":"https://github.com/re-align/just-eval/blob/HEAD/just_eval/evaluate.py","link_basis":"harvester_set","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":"0237f0380d5bf897"}},{"code_sha256_prefix":"a9d15e4437a4a672","entry":"openai_chat_request","repo":"re-align/just-eval","repo_kind":"listed","path":"just_eval/utils.py","file_url":"https://github.com/re-align/just-eval/blob/HEAD/just_eval/utils.py","link_basis":"harvester_set","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":"a9d15e4437a4a672"}},{"code_sha256_prefix":"0f1a589f162138ec","entry":"report","repo":"re-align/just-eval","repo_kind":"listed","path":"just_eval/evaluate.py","file_url":"https://github.com/re-align/just-eval/blob/HEAD/just_eval/evaluate.py","link_basis":"harvester_set","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":"0f1a589f162138ec"}},{"code_sha256_prefix":"2a55bf45c6775c40","entry":"retry_handler","repo":"re-align/just-eval","repo_kind":"listed","path":"just_eval/utils.py","file_url":"https://github.com/re-align/just-eval/blob/HEAD/just_eval/utils.py","link_basis":"harvester_set","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":"2a55bf45c6775c40"}},{"code_sha256_prefix":"fbc703529d72b4e1","entry":"shorten","repo":"re-align/just-eval","repo_kind":"listed","path":"just_eval/evaluate.py","file_url":"https://github.com/re-align/just-eval/blob/HEAD/just_eval/evaluate.py","link_basis":"harvester_set","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":"fbc703529d72b4e1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}