{"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/textarena","title":"TextArena","arxiv_id":"2504.11442","date":"2025-04-15","proceeding":null,"authors":["Leon Guertler","Bobby Cheng","Simon Yu","Bo Liu","Leshem Choshen","Cheston Tan"],"abstract":"TextArena is an open-source collection of competitive text-based games for training and evaluation of agentic behavior in Large Language Models (LLMs). It spans 57+ unique environments (including single-player, two-player, and multi-player setups) and allows for easy evaluation of model capabilities via an online-play system (against humans and other submitted models) with real-time TrueSkill scores. Traditional benchmarks rarely assess dynamic social skills such as negotiation, theory of mind, and deception, creating a gap that TextArena addresses. Designed with research, community and extensibility in mind, TextArena emphasizes ease of adding new games, adapting the framework, testing models, playing against the models, and training models. Detailed documentation of environments, games, leaderboard, and examples are available on https://github.com/LeonGuertler/TextArena and https://www.textarena.ai/.","url_abs":"https://arxiv.org/abs/2504.11442v2","url_pdf":"https://arxiv.org/pdf/2504.11442v2.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":"textarena","repo_url":"https://github.com/leonguertler/textarena","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"text-based-games","task_name":"text-based games"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.11442","atlas_url":"https://app.syntology.ai/?focus=2504.11442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11442"}},"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/leonguertler/textarena","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":"ed485b58f28fefe2","entry":"coord_to_rc","repo":"leonguertler/textarena","repo_kind":"official","path":"textarena/envs/Alquerque/env.py","file_url":"https://github.com/leonguertler/textarena/blob/HEAD/textarena/envs/Alquerque/env.py","link_basis":"harvester_set","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":"ed485b58f28fefe2"}},{"code_sha256_prefix":"cc1efc376639ff91","entry":"create_board_str","repo":"leonguertler/textarena","repo_kind":"official","path":"textarena/envs/ThreePlayerTicTacToe/renderer.py","file_url":"https://github.com/leonguertler/textarena/blob/HEAD/textarena/envs/ThreePlayerTicTacToe/renderer.py","link_basis":"harvester_set","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":"cc1efc376639ff91"}},{"code_sha256_prefix":"66407b06d2b99562","entry":"extract_agent_attributes","repo":"leonguertler/textarena","repo_kind":"official","path":"textarena/api.py","file_url":"https://github.com/leonguertler/textarena/blob/HEAD/textarena/api.py","link_basis":"harvester_set","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":"66407b06d2b99562"}},{"code_sha256_prefix":"fe69d863006331c6","entry":"get_deterministic_model_token","repo":"leonguertler/textarena","repo_kind":"official","path":"textarena/api.py","file_url":"https://github.com/leonguertler/textarena/blob/HEAD/textarena/api.py","link_basis":"harvester_set","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":"fe69d863006331c6"}},{"code_sha256_prefix":"a8e9b362566d5ff5","entry":"rc_to_coord","repo":"leonguertler/textarena","repo_kind":"official","path":"textarena/envs/Alquerque/env.py","file_url":"https://github.com/leonguertler/textarena/blob/HEAD/textarena/envs/Alquerque/env.py","link_basis":"harvester_set","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":"a8e9b362566d5ff5"}},{"code_sha256_prefix":"70ba574be6297fbc","entry":"strip_env_variant","repo":"leonguertler/textarena","repo_kind":"official","path":"textarena/api.py","file_url":"https://github.com/leonguertler/textarena/blob/HEAD/textarena/api.py","link_basis":"harvester_set","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":"70ba574be6297fbc"}},{"code_sha256_prefix":"2a595c27e38cf10d","entry":"make","repo":"leonguertler/textarena","repo_kind":"official","path":"textarena/envs/registration.py","file_url":"https://github.com/leonguertler/textarena/blob/HEAD/textarena/envs/registration.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":"2a595c27e38cf10d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}