{"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/gametraversalbenchmark-evaluating-planning","title":"GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps","arxiv_id":"2410.07765","date":"2024-10-10","proceeding":null,"authors":["Muhammad Umair Nasir","Steven James","Julian Togelius"],"abstract":"Large language models (LLMs) have recently demonstrated great success in generating and understanding natural language. While they have also shown potential beyond the domain of natural language, it remains an open question as to what extent and in which way these LLMs can plan. We investigate their planning capabilities by proposing GameTraversalBenchmark (GTB), a benchmark consisting of diverse 2D grid-based game maps. An LLM succeeds if it can traverse through given objectives, with a minimum number of steps and a minimum number of generation errors. We evaluate a number of LLMs on GTB and found that GPT-4-Turbo achieved the highest score of 44.97% on GTB\\_Score (GTBS), a composite score that combines the three above criteria. Furthermore, we preliminarily test large reasoning models, namely o1, which scores $67.84\\%$ on GTBS, indicating that the benchmark remains challenging for current models. Code, data, and documentation are available at https://github.com/umair-nasir14/Game-Traversal-Benchmark.","url_abs":"https://arxiv.org/abs/2410.07765v1","url_pdf":"https://arxiv.org/pdf/2410.07765v1.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":"gametraversalbenchmark-evaluating-planning","repo_url":"https://github.com/umair-nasir14/game-traversal-benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.07765","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07765"}},"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/umair-nasir14/Game-Traversal-Benchmark","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/umair-nasir14/game-traversal-benchmark","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran":4,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"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":"042372dc236f8b87","entry":"calculate_path_length","repo":"umair-nasir14/Game-Traversal-Benchmark","repo_kind":"official","path":"gtb/gtbench.py","file_url":"https://github.com/umair-nasir14/Game-Traversal-Benchmark/blob/HEAD/gtb/gtbench.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"042372dc236f8b87"}},{"code_sha256_prefix":"703b53d7dd7953a7","entry":"extract_slash","repo":"umair-nasir14/game-traversal-benchmark","repo_kind":"official","path":"gtb/utils.py","file_url":"https://github.com/umair-nasir14/game-traversal-benchmark/blob/HEAD/gtb/utils.py","link_basis":"first_harvest_node","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":"703b53d7dd7953a7"}},{"code_sha256_prefix":"1ca7a923399000a1","entry":"grid_to_csv","repo":"umair-nasir14/game-traversal-benchmark","repo_kind":"official","path":"gtb/utils.py","file_url":"https://github.com/umair-nasir14/game-traversal-benchmark/blob/HEAD/gtb/utils.py","link_basis":"first_harvest_node","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":"1ca7a923399000a1"}},{"code_sha256_prefix":"aba872b0f934c1f6","entry":"logcosh","repo":"umair-nasir14/Game-Traversal-Benchmark","repo_kind":"official","path":"gtb/evaluations.py","file_url":"https://github.com/umair-nasir14/Game-Traversal-Benchmark/blob/HEAD/gtb/evaluations.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aba872b0f934c1f6"}},{"code_sha256_prefix":"f56e1e375553041f","entry":"pad_rows_to_max_length","repo":"umair-nasir14/game-traversal-benchmark","repo_kind":"official","path":"gtb/fixers.py","file_url":"https://github.com/umair-nasir14/game-traversal-benchmark/blob/HEAD/gtb/fixers.py","link_basis":"first_harvest_node","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":"f56e1e375553041f"}},{"code_sha256_prefix":"c2ebcad4054be0b8","entry":"remove_extra_special_chars","repo":"umair-nasir14/game-traversal-benchmark","repo_kind":"official","path":"gtb/fixers.py","file_url":"https://github.com/umair-nasir14/game-traversal-benchmark/blob/HEAD/gtb/fixers.py","link_basis":"first_harvest_node","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":"c2ebcad4054be0b8"}},{"code_sha256_prefix":"e29c7994358b3427","entry":"benchmark","repo":"umair-nasir14/game-traversal-benchmark","repo_kind":"official","path":"gtb/gtbench.py","file_url":"https://github.com/umair-nasir14/game-traversal-benchmark/blob/HEAD/gtb/gtbench.py","link_basis":"first_harvest_node","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":"e29c7994358b3427"}},{"code_sha256_prefix":"384f2e6a900f6f6f","entry":"load_image_dict","repo":"umair-nasir14/game-traversal-benchmark","repo_kind":"official","path":"gtb/utils.py","file_url":"https://github.com/umair-nasir14/game-traversal-benchmark/blob/HEAD/gtb/utils.py","link_basis":"first_harvest_node","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":"384f2e6a900f6f6f"}},{"code_sha256_prefix":"0e8b1dd5ad218e51","entry":"run","repo":"umair-nasir14/game-traversal-benchmark","repo_kind":"official","path":"gtb/gtbench.py","file_url":"https://github.com/umair-nasir14/game-traversal-benchmark/blob/HEAD/gtb/gtbench.py","link_basis":"first_harvest_node","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":"0e8b1dd5ad218e51"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}