{"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/reinforced-internal-external-knowledge","title":"Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent","arxiv_id":"2505.07596","date":"2025-05-12","proceeding":null,"authors":["Ziyang Huang","Xiaowei Yuan","Yiming Ju","Jun Zhao","Kang Liu"],"abstract":"Retrieval-augmented generation (RAG) is a common strategy to reduce hallucinations in Large Language Models (LLMs). While reinforcement learning (RL) can enable LLMs to act as search agents by activating retrieval capabilities, existing ones often underutilize their internal knowledge. This can lead to redundant retrievals, potential harmful knowledge conflicts, and increased inference latency. To address these limitations, an efficient and adaptive search agent capable of discerning optimal retrieval timing and synergistically integrating parametric (internal) and retrieved (external) knowledge is in urgent need. This paper introduces the Reinforced Internal-External Knowledge Synergistic Reasoning Agent (IKEA), which could indentify its own knowledge boundary and prioritize the utilization of internal knowledge, resorting to external search only when internal knowledge is deemed insufficient. This is achieved using a novel knowledge-boundary aware reward function and a knowledge-boundary aware training dataset. These are designed for internal-external knowledge synergy oriented RL, incentivizing the model to deliver accurate answers, minimize unnecessary retrievals, and encourage appropriate external searches when its own knowledge is lacking. Evaluations across multiple knowledge reasoning tasks demonstrate that IKEA significantly outperforms baseline methods, reduces retrieval frequency significantly, and exhibits robust generalization capabilities.","url_abs":"https://arxiv.org/abs/2505.07596v1","url_pdf":"https://arxiv.org/pdf/2505.07596v1.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":"reinforced-internal-external-knowledge","repo_url":"https://github.com/hzy312/knowledge-r1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"rag","task_name":"RAG"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.07596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07596"}},"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/hzy312/knowledge-r1","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":"8709b4b7236b87d7","entry":"get_query","repo":"hzy312/knowledge-r1","repo_kind":"listed","path":"infer.py","file_url":"https://github.com/hzy312/knowledge-r1/blob/HEAD/infer.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":"8709b4b7236b87d7"}},{"code_sha256_prefix":"dd73263b8c088bdf","entry":"make_prefix","repo":"hzy312/knowledge-r1","repo_kind":"listed","path":"scripts/data_process/2wiki_knowledge_boundary.py","file_url":"https://github.com/hzy312/knowledge-r1/blob/HEAD/scripts/data_process/2wiki_knowledge_boundary.py","link_basis":"first_harvest_node","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":"dd73263b8c088bdf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}