arXiv:2611.17788v1 Announce Type: new Abstract: In retrieval-augmented generation (RAG), query rewriting serves as a core interface that aligns user intent with external knowledge bases, and its effectiveness directly determines overall system performance. However, generative retrieval faces three critical challenges in real-world deployment: noisy retrieval feedback, the difficulty of jointly optimizing discrete prompt templates and continuous decoding-control parameters, and the limited generalization of static rewriting strategies under semantically complex scenarios. To address these issues, we propose RAG-FGO, a dynamic optimization framework for generative retrieval strategies. RAG-FGO formulates query rewriting as a non-differentiable black-box optimization problem in a mixed discrete-continuous space, and represents prompt templates and decoding parameters as adaptively optimizable query-rewriting agents. The framework performs global search to enable semantic jumps and structural reorganization that escape local optima, while applying local perturbations for fine-grained alignment and precise refinement. In addition, RAG-FGO introduces an elite-preserving memory pool that accumulates high-quality strategies across iterations, thereby mitigating the impact of stochasticity and noisy feedback on optimization stability. Experimental results on a diverse suite of benchmarks demonstrate the effectiveness and robustness of the proposed method, supporting its applicability to complex semantic retrieval tasks.
RAG-FGO: Dynamic Optimization of Query-Rewriting Agents for Generative RAG
Researchers posted arXiv:2611.17788v1, introducing RAG-FGO, a dynamic optimization framework that treats query rewriting in retrieval-augmented generation as a non-differentiable black-box optimization problem in a mixed discrete-continuous space. RAG-FGO represents prompt templates and decoding parameters as adaptively optimizable query-rewriting agents, combining global search for semantic jumps and structural reorganization with local perturbations for fine-grained refinement, plus an elite-preserving memory pool that accumulates high-quality strategies across iterations to reduce the impact of stochasticity and noisy feedback. The authors report that experiments across a diverse suite of benchmarks demonstrate the method's effectiveness and robustness for complex semantic retrieval tasks, though the abstract gives no specific benchmark scores.
Run your AI side-project on zahid.host
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.