{"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/assistrag-boosting-the-potential-of-large","title":"AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant","arxiv_id":"2411.06805","date":"2024-11-11","proceeding":null,"authors":["Yujia Zhou","Zheng Liu","Zhicheng Dou"],"abstract":"The emergence of Large Language Models (LLMs) has significantly advanced natural language processing, but these models often generate factually incorrect information, known as \"hallucination\". Initial retrieval-augmented generation (RAG) methods like the \"Retrieve-Read\" framework was inadequate for complex reasoning tasks. Subsequent prompt-based RAG strategies and Supervised Fine-Tuning (SFT) methods improved performance but required frequent retraining and risked altering foundational LLM capabilities. To cope with these challenges, we propose Assistant-based Retrieval-Augmented Generation (AssistRAG), integrating an intelligent information assistant within LLMs. This assistant manages memory and knowledge through tool usage, action execution, memory building, and plan specification. Using a two-phase training approach, Curriculum Assistant Learning and Reinforced Preference Optimization. AssistRAG enhances information retrieval and decision-making. Experiments show AssistRAG significantly outperforms benchmarks, especially benefiting less advanced LLMs, by providing superior reasoning capabilities and accurate responses.","url_abs":"https://arxiv.org/abs/2411.06805v1","url_pdf":"https://arxiv.org/pdf/2411.06805v1.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":"assistrag-boosting-the-potential-of-large","repo_url":"https://github.com/smallporridge/assistrag","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"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=2411.06805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06805"}},"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/smallporridge/AssistRAG","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/smallporridge/assistrag","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_fixture":2,"unverified":10},"by_repo_kind":{"official":{"samples":13,"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":13,"samples":[{"code_sha256_prefix":"5f05742c58e418b2","entry":"assistant","repo":"smallporridge/assistrag","repo_kind":"official","path":"AssistRAG/code/assistant.py","file_url":"https://github.com/smallporridge/assistrag/blob/HEAD/AssistRAG/code/assistant.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f05742c58e418b2"}},{"code_sha256_prefix":"5f31e26e430a4134","entry":"get_llama_answer","repo":"smallporridge/assistrag","repo_kind":"official","path":"AssistRAG/code/assistant.py","file_url":"https://github.com/smallporridge/assistrag/blob/HEAD/AssistRAG/code/assistant.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f31e26e430a4134"}},{"code_sha256_prefix":"916a6c0d5ce5b43b","entry":"get_llm_answer","repo":"smallporridge/assistrag","repo_kind":"official","path":"AssistRAG/code/assistant.py","file_url":"https://github.com/smallporridge/assistrag/blob/HEAD/AssistRAG/code/assistant.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"916a6c0d5ce5b43b"}},{"code_sha256_prefix":"da78af27b71bc211","entry":"average_pool","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/WikiSearcher.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/WikiSearcher.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":"da78af27b71bc211"}},{"code_sha256_prefix":"c22bebebf87a4a31","entry":"batch_encode","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/WikiSearcher.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/WikiSearcher.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":"c22bebebf87a4a31"}},{"code_sha256_prefix":"bf8f73a6fb07d884","entry":"format_ref","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/utils.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/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":"bf8f73a6fb07d884"}},{"code_sha256_prefix":"8a9b608065fdfa02","entry":"get_all_alias","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/evaluate.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/evaluate.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":"8a9b608065fdfa02"}},{"code_sha256_prefix":"1e37d433f1dae351","entry":"get_falcon_answer","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/temporal.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/temporal.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":"1e37d433f1dae351"}},{"code_sha256_prefix":"196463fb676c6886","entry":"get_llama_answer","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/generator.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/generator.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":"196463fb676c6886"}},{"code_sha256_prefix":"1ccc18143a9871e1","entry":"get_llama_answer","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/temporal.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/temporal.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":"1ccc18143a9871e1"}},{"code_sha256_prefix":"3f0a20902ba1013e","entry":"get_openai_answer","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/temporal.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/temporal.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":"3f0a20902ba1013e"}},{"code_sha256_prefix":"42853919903b9b2e","entry":"load_dataset","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/utils.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/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":"42853919903b9b2e"}},{"code_sha256_prefix":"18241445ac2dce62","entry":"num_tokens","repo":"smallporridge/AssistRAG","repo_kind":"official","path":"AssistRAG/code/utils.py","file_url":"https://github.com/smallporridge/AssistRAG/blob/HEAD/AssistRAG/code/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":"18241445ac2dce62"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}