{"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-language-model-agency-through","title":"Evaluating Language Model Agency through Negotiations","arxiv_id":"2401.04536","date":"2024-01-09","proceeding":null,"authors":["Tim R. Davidson","Veniamin Veselovsky","Martin Josifoski","Maxime Peyrard","Antoine Bosselut","Michal Kosinski","Robert West"],"abstract":"We introduce an approach to evaluate language model (LM) agency using negotiation games. This approach better reflects real-world use cases and addresses some of the shortcomings of alternative LM benchmarks. Negotiation games enable us to study multi-turn, and cross-model interactions, modulate complexity, and side-step accidental evaluation data leakage. We use our approach to test six widely used and publicly accessible LMs, evaluating performance and alignment in both self-play and cross-play settings. Noteworthy findings include: (i) only closed-source models tested here were able to complete these tasks; (ii) cooperative bargaining games proved to be most challenging to the models; and (iii) even the most powerful models sometimes \"lose\" to weaker opponents","url_abs":"https://arxiv.org/abs/2401.04536v2","url_pdf":"https://arxiv.org/pdf/2401.04536v2.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-language-model-agency-through","repo_url":"https://github.com/epfl-dlab/lamen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"evaluating-language-model-agency-through","repo_url":"https://github.com/leonguertler/textarena","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[{"slug":"lamen-transcripts","name":"LAMEN Transcripts","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2401.04536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04536"}},"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":"deterministic:regex_extraction","url":"https://github.com/epfl-dlab/LAMEN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/epfl-dlab/lamen","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leonguertler/textarena","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"ce662efe0ac1fbb1","entry":"check_if_model_instantiated","repo":"epfl-dlab/LAMEN","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/epfl-dlab/LAMEN/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce662efe0ac1fbb1"}},{"code_sha256_prefix":"3bb422770073a45e","entry":"extract_dictionary","repo":"epfl-dlab/LAMEN","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/epfl-dlab/LAMEN/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bb422770073a45e"}},{"code_sha256_prefix":"d6877bfa047c0336","entry":"fuzzy_index_matching","repo":"epfl-dlab/LAMEN","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/epfl-dlab/LAMEN/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6877bfa047c0336"}},{"code_sha256_prefix":"1e05e137fdae446b","entry":"load_game","repo":"epfl-dlab/LAMEN","repo_kind":"official","path":"src/games.py","file_url":"https://github.com/epfl-dlab/LAMEN/blob/HEAD/src/games.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e05e137fdae446b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}