{"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/evaluating-the-goal-directedness-of-large","title":"Evaluating the Goal-Directedness of Large Language Models","arxiv_id":"2504.11844","date":"2025-04-16","proceeding":null,"authors":["Tom Everitt","Cristina Garbacea","Alexis Bellot","Jonathan Richens","Henry Papadatos","Siméon Campos","Rohin Shah"],"abstract":"To what extent do LLMs use their capabilities towards their given goal? We take this as a measure of their goal-directedness. We evaluate goal-directedness on tasks that require information gathering, cognitive effort, and plan execution, where we use subtasks to infer each model's relevant capabilities. Our evaluations of LLMs from Google DeepMind, OpenAI, and Anthropic show that goal-directedness is relatively consistent across tasks, differs from task performance, and is only moderately sensitive to motivational prompts. Notably, most models are not fully goal-directed. We hope our goal-directedness evaluations will enable better monitoring of LLM progress, and enable more deliberate design choices of agentic properties in LLMs.","url_abs":"https://arxiv.org/abs/2504.11844v1","url_pdf":"https://arxiv.org/pdf/2504.11844v1.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":"evaluating-the-goal-directedness-of-large","repo_url":"https://github.com/Crista23/goal_directedness_llms","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.11844","atlas_url":"https://app.syntology.ai/?focus=2504.11844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11844"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Crista23/goal_directedness_llms","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"8a45b8fb7371f957","entry":"all_configurations","repo":"Crista23/goal_directedness_llms","repo_kind":"official","path":"tasks/full_task.py","file_url":"https://github.com/Crista23/goal_directedness_llms/blob/HEAD/tasks/full_task.py","link_basis":"harvester_set","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":"8a45b8fb7371f957"}},{"code_sha256_prefix":"96bfb123e4e7d1be","entry":"generate_block_names","repo":"Crista23/goal_directedness_llms","repo_kind":"official","path":"analysis/expected_return.py","file_url":"https://github.com/Crista23/goal_directedness_llms/blob/HEAD/analysis/expected_return.py","link_basis":"harvester_set","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":"96bfb123e4e7d1be"}},{"code_sha256_prefix":"90ce0031c7ec0aa7","entry":"goal_directedness","repo":"Crista23/goal_directedness_llms","repo_kind":"official","path":"analysis/goal_directedness.py","file_url":"https://github.com/Crista23/goal_directedness_llms/blob/HEAD/analysis/goal_directedness.py","link_basis":"harvester_set","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":"90ce0031c7ec0aa7"}},{"code_sha256_prefix":"77f7c3f72c89175d","entry":"height_of_tower","repo":"Crista23/goal_directedness_llms","repo_kind":"official","path":"analysis/expected_return.py","file_url":"https://github.com/Crista23/goal_directedness_llms/blob/HEAD/analysis/expected_return.py","link_basis":"harvester_set","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":"77f7c3f72c89175d"}},{"code_sha256_prefix":"88d4f1ad7f0ecb97","entry":"height_of_tower","repo":"Crista23/goal_directedness_llms","repo_kind":"official","path":"tasks/full_task.py","file_url":"https://github.com/Crista23/goal_directedness_llms/blob/HEAD/tasks/full_task.py","link_basis":"harvester_set","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":"88d4f1ad7f0ecb97"}},{"code_sha256_prefix":"44ac126e906a6bf1","entry":"list_to_natural_language","repo":"Crista23/goal_directedness_llms","repo_kind":"official","path":"blocksworld_environment/blocksworld_environment.py","file_url":"https://github.com/Crista23/goal_directedness_llms/blob/HEAD/blocksworld_environment/blocksworld_environment.py","link_basis":"harvester_set","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":"44ac126e906a6bf1"}},{"code_sha256_prefix":"bb22736701cd8662","entry":"score","repo":"Crista23/goal_directedness_llms","repo_kind":"official","path":"tasks/full_task.py","file_url":"https://github.com/Crista23/goal_directedness_llms/blob/HEAD/tasks/full_task.py","link_basis":"harvester_set","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":"bb22736701cd8662"}},{"code_sha256_prefix":"91f49f5213bcb3eb","entry":"load_dataframe","repo":"Crista23/goal_directedness_llms","repo_kind":"official","path":"analysis/expected_return.py","file_url":"https://github.com/Crista23/goal_directedness_llms/blob/HEAD/analysis/expected_return.py","link_basis":"harvester_set","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":"91f49f5213bcb3eb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}