REVIEW 14 cited by
Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy
Not yet reviewed by Pith; the record is open.
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
read the original abstract
Large language models are powerful text processors and reasoners, but are still subject to limitations including outdated knowledge and hallucinations, which necessitates connecting them to the world. Retrieval-augmented large language models have raised extensive attention for grounding model generation on external knowledge. However, retrievers struggle to capture relevance, especially for queries with complex information needs. Recent work has proposed to improve relevance modeling by having large language models actively involved in retrieval, i.e., to improve retrieval with generation. In this paper, we show that strong performance can be achieved by a method we call Iter-RetGen, which synergizes retrieval and generation in an iterative manner. A model output shows what might be needed to finish a task, and thus provides an informative context for retrieving more relevant knowledge which in turn helps generate a better output in the next iteration. Compared with recent work which interleaves retrieval with generation when producing an output, Iter-RetGen processes all retrieved knowledge as a whole and largely preserves the flexibility in generation without structural constraints. We evaluate Iter-RetGen on multi-hop question answering, fact verification, and commonsense reasoning, and show that it can flexibly leverage parametric knowledge and non-parametric knowledge, and is superior to or competitive with state-of-the-art retrieval-augmented baselines while causing fewer overheads of retrieval and generation. We can further improve performance via generation-augmented retrieval adaptation.
Forward citations
Cited by 14 Pith papers
-
When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
On ChemKGMultiHopQA, iterative retrieval-reasoning outperformed oracle gold-context static RAG for all 11 LLMs tested, with gains up to 25.6 percentage points.
-
Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning
Rewarding each parallel reasoning path by Monte-Carlo-Shapley marginal contribution, scored by a generative reward model, lifts Pass@16 on AIME24/AIME25/AMC23 by 4-90% relative over Parallel-R1 with a fifth of the tra...
-
Reliable Post-Retrieval Assembly for Agent Memory: Separating Evidence Extraction from Policy Execution
With serial-numbered facts, swapping LLM judgment for direct candidate extraction plus Python max(serial) lifts MAB FactConsolidation to 78/95% single-hop and 30/51% multi-hop, beating all 22 published systems at 262K...
-
Efficient Multi-round LLM Inference over Disaggregated Serving
AMPD adaptively routes incremental prefill tasks between prefill and decode workers and reorders queued prefill jobs to improve SLO attainment for multi-round LLM inference under prefill-decode disaggregation.
-
MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning
The paper advertises a self-evolving tool-using agent that beats baselines, but the body contains a different math paper, leaving the performance claims unsupported.
-
HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving
HedraRAG uses a graph abstraction and dynamic transformations to pipeline generation and retrieval stages, achieving 1.5x to 5x speedups in heterogeneous RAG serving.
-
Shifting from Ranking to Set Selection for Retrieval Augmented Generation
SETR identifies a query's information requirements with chain-of-thought reasoning and selects a compact passage set, improving multi-hop RAG accuracy over fixed-top-k reranking baselines.
-
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization
LeTS hybridizes process-level and outcome-level rewards for GRPO-based RAG training, improving accuracy and reducing redundant searches on multi-hop QA benchmarks.
-
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
A multi-agent web-search framework that stores progress in shared evidence, coverage, and failure state reports the best F1 scores among compared baselines on WideSearch (80.3 item F1) and GISA (76.5 set F1).
-
GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework
GOSU globally merges semantic units from text chunks into a unit-centric knowledge graph and uses three-tier keyword retrieval to improve RAG generation quality, according to LLM-judge win rates.
-
KnowCoder-V2: Deep Knowledge Analysis
KnowCoder-V2 augments deep research with offline knowledge organization and code-based knowledge computation, reporting gains on information extraction, KBQA, and LLM-judged report generation.
-
R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
R1-Searcher++ uses SFT cold-start plus reinforcement learning with group and memorization rewards to teach Qwen-2.5-7B to balance internal knowledge and external retrieval, improving accuracy and reducing retrieval calls.
-
Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework
A multi-agent LLM framework generates synthetic QA datasets for RAG evaluation by combining clustering-based sampling, PII pseudonymization, and QA curation, with reported diversity gains and 0.75-0.90 masking accuracy.
-
Question Decomposition for Retrieval-Augmented Generation
Splitting multi-hop questions into subquestions and reranking the merged retrieval pool improves RAG evidence coverage and answer accuracy on MultiHop-RAG and HotpotQA.
Discussion (0). Continue with ORCID to comment.