Pith. sign in

REVIEW 5 cited by

SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.18141 v2 pith:EKBLNK3J submitted 2024-10-22 cs.IR cs.AIcs.CL

Jingsheng Gao , Linxu Li , Weiyuan Li , Yuzhuo Fu , Bin Dai This is my paper
classification cs.IRcs.AIcs.CL
keywords jointlymodulesoptimizedsystemachieveperformancesmartragbest
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

RAG systems consist of multiple modules to work together. However, these modules are usually separately trained. We argue that a system like RAG that incorporates multiple modules should be jointly optimized to achieve optimal performance. To demonstrate this, we design a specific pipeline called \textbf{SmartRAG} that includes a policy network and a retriever. The policy network can serve as 1) a decision maker that decides when to retrieve, 2) a query rewriter to generate a query most suited to the retriever, and 3) an answer generator that produces the final response with/without the observations. We then propose to jointly optimize the whole system using a reinforcement learning algorithm, with the reward designed to encourage the system to achieve the best performance with minimal retrieval cost. When jointly optimized, all the modules can be aware of how other modules are working and thus find the best way to work together as a complete system. Empirical results demonstrate that the jointly optimized SmartRAG can achieve better performance than separately optimized counterparts.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering

    cs.CL 2026-01 conditional novelty 7.0 of 10

    On ChemKGMultiHopQA, iterative retrieval-reasoning outperformed oracle gold-context static RAG for all 11 LLMs tested, with gains up to 25.6 percentage points.

  2. Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain

    cs.IR 2025-09 conditional novelty 6.0 of 10

    Misleading health documents in RAG context sharply lower LLM accuracy, and heavily helpful-biased retrieval pools restore it.

  3. The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems

    cs.IR 2025-05 conditional novelty 6.0 of 10

    A reinforcement-learning attack that swaps a few words in a single document pushes it into a black-box RAG system's top-3 results and flips the generated answer around 45-47% of the time.

  4. Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation

    cs.CL 2025-05 reject novelty 5.0 of 10

    EVO-RAG applies curriculum-guided reinforcement learning with time-varying reward weights to multi-hop RAG, reporting improved EM on HotpotQA, 2WikiMultiHopQA, and MuSiQue.

  5. Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems

    cs.IR 2025-05 conditional novelty 5.0 of 10

    Wrapping erroneous knowledge in a reasoning model's own chain-of-thought template raises poisoning attack success on an R1-based RAG system by 10 percentage points over the strongest prior method in a 100-query MS MARCO test.

Pith tools