{"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/language-models-can-solve-computer-tasks","title":"Language Models can Solve Computer Tasks","arxiv_id":"2303.17491","date":"2023-03-30","proceeding":"NeurIPS 2023 11","authors":["Geunwoo Kim","Pierre Baldi","Stephen Mcaleer"],"abstract":"Agents capable of carrying out general tasks on a computer can improve efficiency and productivity by automating repetitive tasks and assisting in complex problem-solving. Ideally, such agents should be able to solve new computer tasks presented to them through natural language commands. However, previous approaches to this problem require large amounts of expert demonstrations and task-specific reward functions, both of which are impractical for new tasks. In this work, we show that a pre-trained large language model (LLM) agent can execute computer tasks guided by natural language using a simple prompting scheme where the agent Recursively Criticizes and Improves its output (RCI). The RCI approach significantly outperforms existing LLM methods for automating computer tasks and surpasses supervised learning (SL) and reinforcement learning (RL) approaches on the MiniWoB++ benchmark. We compare multiple LLMs and find that RCI with the InstructGPT-3+RLHF LLM is state-of-the-art on MiniWoB++, using only a handful of demonstrations per task rather than tens of thousands, and without a task-specific reward function. Furthermore, we demonstrate RCI prompting's effectiveness in enhancing LLMs' reasoning abilities on a suite of natural language reasoning tasks, outperforming chain of thought (CoT) prompting with external feedback. We find that RCI combined with CoT performs better than either separately. Our code can be found here: https://github.com/posgnu/rci-agent.","url_abs":"https://arxiv.org/abs/2303.17491v3","url_pdf":"https://arxiv.org/pdf/2303.17491v3.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":"language-models-can-solve-computer-tasks","repo_url":"https://github.com/posgnu/rci-agent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.17491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17491"}},"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/posgnu/rci-agent","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"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":"7f932a7eac5a840a","entry":"extract_click_checkboxes","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/fields.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/fields.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":"7f932a7eac5a840a"}},{"code_sha256_prefix":"09db1eb1eb3d66a6","entry":"extract_click_checkboxes_soft","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/fields.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/fields.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":"09db1eb1eb3d66a6"}},{"code_sha256_prefix":"7fd716eeb200413a","entry":"find_sublist","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/utils.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/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":"7fd716eeb200413a"}},{"code_sha256_prefix":"fd646d427848e7ee","entry":"get_click_checkboxes_hard","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/reward.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/reward.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":"fd646d427848e7ee"}},{"code_sha256_prefix":"5b2c9e8b14418640","entry":"get_field_extractor","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/fields.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/fields.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":"5b2c9e8b14418640"}},{"code_sha256_prefix":"14e9be149aace800","entry":"get_original_reward","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/reward.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/reward.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":"14e9be149aace800"}},{"code_sha256_prefix":"ed9cdb15ddb55957","entry":"get_raw_reward","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/reward.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/reward.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":"ed9cdb15ddb55957"}},{"code_sha256_prefix":"3973a30170a6113a","entry":"get_screenshot","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/screenshot.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/screenshot.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":"3973a30170a6113a"}},{"code_sha256_prefix":"962335f24b95d8c0","entry":"pil_to_numpy_array","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/screenshot.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/screenshot.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":"962335f24b95d8c0"}},{"code_sha256_prefix":"28f90015263219d5","entry":"strip_punctuation","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/utils.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/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":"28f90015263219d5"}},{"code_sha256_prefix":"9793a008041e04f6","entry":"strip_whitespace","repo":"posgnu/rci-agent","repo_kind":"official","path":"computergym/computergym/miniwob/miniwob_interface/utils.py","file_url":"https://github.com/posgnu/rci-agent/blob/HEAD/computergym/computergym/miniwob/miniwob_interface/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":"9793a008041e04f6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}