{"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/adapting-to-non-stationary-environments-multi","title":"Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs","arxiv_id":"2412.07618","date":"2024-12-10","proceeding":null,"authors":["Xiaqiang Tang","Jian Li","Nan Du","Sihong Xie"],"abstract":"Despite the superior performance of Large language models on many NLP tasks, they still face significant limitations in memorizing extensive world knowledge. Recent studies have demonstrated that leveraging the Retrieval-Augmented Generation (RAG) framework, combined with Knowledge Graphs that encapsulate extensive factual data in a structured format, robustly enhances the reasoning capabilities of LLMs. However, deploying such systems in real-world scenarios presents challenges: the continuous evolution of non-stationary environments may lead to performance degradation and user satisfaction requires a careful balance of performance and responsiveness. To address these challenges, we introduce a Multi-objective Multi-Armed Bandit enhanced RAG framework, supported by multiple retrieval methods with diverse capabilities under rich and evolving retrieval contexts in practice. Within this framework, each retrieval method is treated as a distinct ``arm''. The system utilizes real-time user feedback to adapt to dynamic environments, by selecting the appropriate retrieval method based on input queries and the historical multi-objective performance of each arm. Extensive experiments conducted on two benchmark KGQA datasets demonstrate that our method significantly outperforms baseline methods in non-stationary settings while achieving state-of-the-art performance in stationary environments. Code and data are available at https://github.com/FUTUREEEEEE/Dynamic-RAG.git","url_abs":"https://arxiv.org/abs/2412.07618v2","url_pdf":"https://arxiv.org/pdf/2412.07618v2.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":"adapting-to-non-stationary-environments-multi","repo_url":"https://github.com/futureeeeee/dynamic-rag","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"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":"https://syntology.ai/paper/2412.07618","atlas_url":"https://app.syntology.ai/?focus=2412.07618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07618"}},"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/futureeeeee/dynamic-rag","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":"69e582d84850bb60","entry":"softmax","repo":"futureeeeee/dynamic-rag","repo_kind":"official","path":"utils.py","file_url":"https://github.com/futureeeeee/dynamic-rag/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"69e582d84850bb60"}},{"code_sha256_prefix":"6acfe88d09a11a54","entry":"compute_metrics","repo":"futureeeeee/dynamic-rag","repo_kind":"official","path":"nn_router.py","file_url":"https://github.com/futureeeeee/dynamic-rag/blob/HEAD/nn_router.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6acfe88d09a11a54"}},{"code_sha256_prefix":"7ac17353eba9bc3d","entry":"load_model","repo":"futureeeeee/dynamic-rag","repo_kind":"official","path":"nn_router.py","file_url":"https://github.com/futureeeeee/dynamic-rag/blob/HEAD/nn_router.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ac17353eba9bc3d"}},{"code_sha256_prefix":"6008a0f769373e64","entry":"multi_label_metrics","repo":"futureeeeee/dynamic-rag","repo_kind":"official","path":"nn_router.py","file_url":"https://github.com/futureeeeee/dynamic-rag/blob/HEAD/nn_router.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6008a0f769373e64"}},{"code_sha256_prefix":"884fefcc0d37c80e","entry":"prepare_prompts","repo":"futureeeeee/dynamic-rag","repo_kind":"official","path":"utils.py","file_url":"https://github.com/futureeeeee/dynamic-rag/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"884fefcc0d37c80e"}},{"code_sha256_prefix":"22d39c4ec95ef984","entry":"print_on_first_call","repo":"futureeeeee/dynamic-rag","repo_kind":"official","path":"utils.py","file_url":"https://github.com/futureeeeee/dynamic-rag/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"22d39c4ec95ef984"}},{"code_sha256_prefix":"ceec98f51a5040dd","entry":"update_metric","repo":"futureeeeee/dynamic-rag","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/futureeeeee/dynamic-rag/blob/HEAD/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ceec98f51a5040dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}