{"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/planrag-a-plan-then-retrieval-augmented","title":"PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers","arxiv_id":"2406.12430","date":"2024-06-18","proceeding":null,"authors":["Myeonghwa Lee","Seonho An","Min-Soo Kim"],"abstract":"In this paper, we conduct a study to utilize LLMs as a solution for decision making that requires complex data analysis. We define Decision QA as the task of answering the best decision, $d_{best}$, for a decision-making question $Q$, business rules $R$ and a database $D$. Since there is no benchmark that can examine Decision QA, we propose Decision QA benchmark, DQA. It has two scenarios, Locating and Building, constructed from two video games (Europa Universalis IV and Victoria 3) that have almost the same goal as Decision QA. To address Decision QA effectively, we also propose a new RAG technique called the iterative plan-then-retrieval augmented generation (PlanRAG). Our PlanRAG-based LM generates the plan for decision making as the first step, and the retriever generates the queries for data analysis as the second step. The proposed method outperforms the state-of-the-art iterative RAG method by 15.8% in the Locating scenario and by 7.4% in the Building scenario, respectively. We release our code and benchmark at https://github.com/myeon9h/PlanRAG.","url_abs":"https://arxiv.org/abs/2406.12430v1","url_pdf":"https://arxiv.org/pdf/2406.12430v1.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":"planrag-a-plan-then-retrieval-augmented","repo_url":"https://github.com/myeon9h/planrag","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"rag","method_name":"RAG"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.12430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12430"}},"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/myeon9h/PlanRAG","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"ba6c7ed4a5b6a3f6","entry":"building_dataloader","repo":"myeon9h/PlanRAG","repo_kind":"official","path":"src/data_loaders/building.py","file_url":"https://github.com/myeon9h/PlanRAG/blob/HEAD/src/data_loaders/building.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":"ba6c7ed4a5b6a3f6"}},{"code_sha256_prefix":"901a9d19750450ea","entry":"building_fewshot","repo":"myeon9h/PlanRAG","repo_kind":"official","path":"src/data_loaders/fewshot_loader.py","file_url":"https://github.com/myeon9h/PlanRAG/blob/HEAD/src/data_loaders/fewshot_loader.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":"901a9d19750450ea"}},{"code_sha256_prefix":"991d88a09372efdf","entry":"fake_tool","repo":"myeon9h/PlanRAG","repo_kind":"official","path":"src/experimental_multiAgents.py","file_url":"https://github.com/myeon9h/PlanRAG/blob/HEAD/src/experimental_multiAgents.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":"991d88a09372efdf"}},{"code_sha256_prefix":"c5c5ae6bd284d2f1","entry":"locating_dataloader","repo":"myeon9h/PlanRAG","repo_kind":"official","path":"src/data_loaders/locating.py","file_url":"https://github.com/myeon9h/PlanRAG/blob/HEAD/src/data_loaders/locating.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":"c5c5ae6bd284d2f1"}},{"code_sha256_prefix":"4ed499e188f19a07","entry":"locating_fewshot","repo":"myeon9h/PlanRAG","repo_kind":"official","path":"src/data_loaders/fewshot_loader.py","file_url":"https://github.com/myeon9h/PlanRAG/blob/HEAD/src/data_loaders/fewshot_loader.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":"4ed499e188f19a07"}},{"code_sha256_prefix":"9cffe3c7edd1d9d3","entry":"fewshot_loader","repo":"myeon9h/PlanRAG","repo_kind":"official","path":"src/data_loaders/fewshot_loader.py","file_url":"https://github.com/myeon9h/PlanRAG/blob/HEAD/src/data_loaders/fewshot_loader.py","link_basis":"first_harvest_node","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":"9cffe3c7edd1d9d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}