{"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/goal-a-generalist-combinatorial-optimization","title":"GOAL: A Generalist Combinatorial Optimization Agent Learning","arxiv_id":"2406.15079","date":"2024-06-21","proceeding":null,"authors":["Darko Drakulic","Sofia Michel","Jean-Marc Andreoli"],"abstract":"Machine Learning-based heuristics have recently shown impressive performance in solving a variety of hard combinatorial optimization problems (COPs). However they generally rely on a separate neural model, specialized and trained for each single problem. Any variation of a problem requires adjustment of its model and re-training from scratch. In this paper, we propose GOAL (for Generalist combinatorial Optimization Agent Learning), a generalist model capable of efficiently solving multiple COPs and which can be fine-tuned to solve new COPs. GOAL consists of a single backbone plus light-weight problem-specific adapters for input and output processing. The backbone is based on a new form of mixed-attention blocks which allows to handle problems defined on graphs with arbitrary combinations of node, edge and instance-level features. Additionally, problems which involve heterogeneous types of nodes or edges are handled through a novel multi-type transformer architecture, where the attention blocks are duplicated to attend the meaningful combinations of types while relying on the same shared parameters. We train GOAL on a set of routing, scheduling and classic graph problems and show that it is only slightly inferior to the specialized baselines while being the first multi-task model that solves a wide range of COPs. Finally we showcase the strong transfer learning capacity of GOAL by fine-tuning it on several new problems. Our code is available at https://github.com/naver/goal-co/.","url_abs":"https://arxiv.org/abs/2406.15079v2","url_pdf":"https://arxiv.org/pdf/2406.15079v2.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":"goal-a-generalist-combinatorial-optimization","repo_url":"https://github.com/naver/goal-co","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"combinatorial-optimization","task_name":"Combinatorial Optimization"},{"task_slug":"scheduling","task_name":"Scheduling"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.15079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15079"}},"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/naver/goal-co","reach":null}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":7,"samples":[{"code_sha256_prefix":"2bd36da6a44d602c","entry":"MultiHeadAttention","repo":"naver/goal-co","repo_kind":"official","path":"model/goal.py","file_url":"https://github.com/naver/goal-co/blob/HEAD/model/goal.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2bd36da6a44d602c"}},{"code_sha256_prefix":"87c3247476434eba","entry":"NodeAdapter","repo":"naver/goal-co","repo_kind":"official","path":"model/goal.py","file_url":"https://github.com/naver/goal-co/blob/HEAD/model/goal.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"87c3247476434eba"}},{"code_sha256_prefix":"fdff959b3c32f2c8","entry":"OutputAdapter","repo":"naver/goal-co","repo_kind":"official","path":"model/goal.py","file_url":"https://github.com/naver/goal-co/blob/HEAD/model/goal.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fdff959b3c32f2c8"}},{"code_sha256_prefix":"e9ed6e57077edb7d","entry":"EdgeAdapter","repo":"naver/goal-co","repo_kind":"official","path":"model/goal.py","file_url":"https://github.com/naver/goal-co/blob/HEAD/model/goal.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e9ed6e57077edb7d"}},{"code_sha256_prefix":"86fb44a114d5d930","entry":"GOAL","repo":"naver/goal-co","repo_kind":"official","path":"model/goal.py","file_url":"https://github.com/naver/goal-co/blob/HEAD/model/goal.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"86fb44a114d5d930"}},{"code_sha256_prefix":"e25d388b98c8e3f0","entry":"Layer","repo":"naver/goal-co","repo_kind":"official","path":"model/goal.py","file_url":"https://github.com/naver/goal-co/blob/HEAD/model/goal.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e25d388b98c8e3f0"}},{"code_sha256_prefix":"fdfed8c3091101c8","entry":"ResidualNorm","repo":"naver/goal-co","repo_kind":"official","path":"model/goal.py","file_url":"https://github.com/naver/goal-co/blob/HEAD/model/goal.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fdfed8c3091101c8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}