{"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/c-3po-compact-plug-and-play-proxy","title":"C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation","arxiv_id":"2502.06205","date":"2025-02-10","proceeding":null,"authors":["Guoxin Chen","Minpeng Liao","Peiying Yu","Dingmin Wang","Zile Qiao","Chao Yang","Xin Zhao","Kai Fan"],"abstract":"Retrieval-augmented generation (RAG) systems face a fundamental challenge in aligning independently developed retrievers and large language models (LLMs). Existing approaches typically involve modifying either component or introducing simple intermediate modules, resulting in practical limitations and sub-optimal performance. Inspired by human search behavior -- typically involving a back-and-forth process of proposing search queries and reviewing documents, we propose C-3PO, a proxy-centric framework that facilitates communication between retrievers and LLMs through a lightweight multi-agent system. Our framework implements three specialized agents that collaboratively optimize the entire RAG pipeline without altering the retriever and LLMs. These agents work together to assess the need for retrieval, generate effective queries, and select information suitable for the LLMs. To enable effective multi-agent coordination, we develop a tree-structured rollout approach for reward credit assignment in reinforcement learning. Extensive experiments in both in-domain and out-of-distribution scenarios demonstrate that C-3PO significantly enhances RAG performance while maintaining plug-and-play flexibility and superior generalization capabilities.","url_abs":"https://arxiv.org/abs/2502.06205v2","url_pdf":"https://arxiv.org/pdf/2502.06205v2.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":[],"tasks":[{"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":{"atlas_url":"https://app.syntology.ai/?focus=2502.06205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06205"}},"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/Chen-GX/C-3PO","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"found_in_text":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"53d425eb1278ddda","entry":"load_json","repo":"Chen-GX/C-3PO","repo_kind":"found_in_text","path":"C-3PO/utils.py","file_url":"https://github.com/Chen-GX/C-3PO/blob/HEAD/C-3PO/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53d425eb1278ddda"}},{"code_sha256_prefix":"25737e9971bb7fb6","entry":"compute_str_em","repo":"Chen-GX/C-3PO","repo_kind":"found_in_text","path":"C-3PO/metrics.py","file_url":"https://github.com/Chen-GX/C-3PO/blob/HEAD/C-3PO/metrics.py","link_basis":"harvester_set","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":"25737e9971bb7fb6"}},{"code_sha256_prefix":"747beef3be6e23fb","entry":"exact_presence","repo":"Chen-GX/C-3PO","repo_kind":"found_in_text","path":"C-3PO/metrics.py","file_url":"https://github.com/Chen-GX/C-3PO/blob/HEAD/C-3PO/metrics.py","link_basis":"harvester_set","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":"747beef3be6e23fb"}},{"code_sha256_prefix":"2c04a8129a94b08e","entry":"load_data","repo":"Chen-GX/C-3PO","repo_kind":"found_in_text","path":"C-3PO/utils.py","file_url":"https://github.com/Chen-GX/C-3PO/blob/HEAD/C-3PO/utils.py","link_basis":"harvester_set","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":"2c04a8129a94b08e"}},{"code_sha256_prefix":"b27698eecee6ba64","entry":"load_jsonl","repo":"Chen-GX/C-3PO","repo_kind":"found_in_text","path":"C-3PO/utils.py","file_url":"https://github.com/Chen-GX/C-3PO/blob/HEAD/C-3PO/utils.py","link_basis":"harvester_set","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":"b27698eecee6ba64"}},{"code_sha256_prefix":"37e0a25b59a4cc3e","entry":"normalize_answer","repo":"Chen-GX/C-3PO","repo_kind":"found_in_text","path":"C-3PO/metrics.py","file_url":"https://github.com/Chen-GX/C-3PO/blob/HEAD/C-3PO/metrics.py","link_basis":"harvester_set","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":"37e0a25b59a4cc3e"}},{"code_sha256_prefix":"02d3afce165ef02f","entry":"read_and_check_ip","repo":"Chen-GX/C-3PO","repo_kind":"found_in_text","path":"C-3PO/llm_server.py","file_url":"https://github.com/Chen-GX/C-3PO/blob/HEAD/C-3PO/llm_server.py","link_basis":"harvester_set","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":"02d3afce165ef02f"}},{"code_sha256_prefix":"4d02ca6140f4405a","entry":"str2bool","repo":"Chen-GX/C-3PO","repo_kind":"found_in_text","path":"C-3PO/arguments.py","file_url":"https://github.com/Chen-GX/C-3PO/blob/HEAD/C-3PO/arguments.py","link_basis":"harvester_set","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":"4d02ca6140f4405a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}