4arXiv cs.AI (Artificial Intelligence)·
APS-RAG: Corrective agentic hybrid RAG system deployed at Advanced Photon Source with operations-grounded evaluation
Researchers present APS-RAG, a deployed retrieval-augmented generation platform for the Advanced Photon Source (APS) scientific facility that fuses dense, sparse, and knowledge-graph retrieval channels with a corrective agentic loop and a ReAct executor over an MCP tooling layer. The system is evaluated on APS-Bench, a new 50-question QA dataset with auditable gold answers, where the full corrective Agentic GraphRAG achieves 70.3% strict vital-nugget recall versus 63.8% for a BM25 baseline. The cross-encoder reranker is identified as the most impactful component, with its removal causing a 32.8% drop in recall. The codebase, evaluation harness, and benchmark construction methodology are released to support adoption at other scientific facilities.
Related guides (3)
Related events (8)
GRADRAG: Cross-component prompt adaptation for coordinated multi-agent RAG pipelines
GRADRAG is a new framework that treats a multi-agent RAG pipeline as a computational graph and propagates structured evaluator feedback upstream to iteratively update retriever, graph constructor, and answerer prompts. Unlike prior work that optimizes components in isolation, GRADRAG coordinates improvements across the full pipeline via a Prompt Optimizer and an early-stopping Evaluator. Evaluated on SQUALITY and QMSUM benchmarks under both flat chunk-based and graph-based retrieval paradigms, GRADRAG achieves a 12–15 percentage point net preference margin over one-step refinement baselines in LLM-judged pairwise comparisons.
Comparative framework for RAG variants: when GraphRAG and Agentic RAG are actually needed
A new arXiv preprint introduces a systematic evaluation framework comparing nine standardized RAG scenarios across regular RAG, GraphRAG, Modular RAG, and Agentic RAG on semi-structured knowledge bases. The authors propose a novel context engineering method that reduces token usage by 19–53% for GraphRAG and Agentic RAG by addressing context/memory overflow. A key finding is a 'retrieval-generation gap' where expanded retrieval does not proportionally improve generation quality, suggesting retrieval-oriented metrics overstate the benefits of advanced retrieval. The work targets practitioners building production RAG systems and provides data-driven guidance on when to use each variant.
Anthropic introduces Contextual Retrieval to reduce RAG retrieval failures by up to 67%
Anthropic published a technical method called Contextual Retrieval that combines Contextual Embeddings and Contextual BM25 to address the context-loss problem in traditional RAG pipelines. The approach prepends chunk-level context before encoding, reducing failed retrievals by 49% standalone and 67% when combined with reranking. The post also highlights prompt caching as a simpler alternative for knowledge bases under 200K tokens, and provides a cookbook for deployment with Claude.
Production Agentic RAG Course Repository Gains Traction on GitHub
A GitHub repository titled 'production-agentic-rag-course' by jamwithai has accumulated 6,158 stars with 45 added today, indicating community interest in production-grade agentic retrieval-augmented generation systems. The repository appears to be an educational resource focused on deploying agentic RAG pipelines in production environments. Its trending status reflects ongoing developer demand for practical guidance on agentic and RAG architectures.
LightRAG: Simple and Fast Retrieval-Augmented Generation (EMNLP 2025)
LightRAG is an open-source Python library for retrieval-augmented generation, accepted at EMNLP 2025, with nearly 38,000 GitHub stars. The project emphasizes simplicity and speed in RAG pipelines. Its high star count signals broad practitioner adoption in the RAG tooling space.
RAPS-DA: Regime-aware peer specialization for robust RAG under knowledge conflicts
A new arXiv preprint introduces RAPS-DA, a training framework for making RAG systems more robust when retrieved context conflicts with a model's parametric knowledge. The approach divides conflicts into three reliability regimes (Grounding, Arbitration, Resistance) and trains separate peer specialist models per regime from a shared base, using reverse-KL supervision and a dual-layer token selector to filter uninformative training signals. Peer specialists exist only during training, so the deployed student model requires no additional components at inference time. Experiments across five conflict scenarios and two out-of-distribution benchmarks show RAPS-DA outperforms prompting, decoding, fine-tuning, RL, and single-teacher baselines.
UMG-RAG: Training-free hybrid retrieval with uncertainty-aware granularity fusion for long-document RAG
Researchers propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a training-free hybrid retrieval framework that addresses the tension between large and fine-grained retrieval chunks in RAG pipelines. The system converts dense and sparse retriever scores across multiple chunk granularities into evidence distributions, estimates reliability via entropy, and fuses candidates using query-specific confidence signals. A variant called UMGP-RAG uses fine-grained hits to locate evidence while returning broader parent chunks for coherence. Experiments on QA benchmarks show improved generation quality with no changes to the underlying retriever or generator.
DynaKRAG: Learnable state-conditioned control policy for multi-hop RAG evidence acquisition
DynaKRAG is a new framework that formulates multi-hop retrieval-augmented generation as a state-conditioned control problem over atomic evidence operations (iterative retrieval, query reformulation, sufficiency judging, etc.), using a learned controller to select among valid operations at each step. Evaluated with Qwen2.5-7B-Instruct, it achieves F1 scores of 0.5998 on HotpotQA, 0.5340 on 2WikiMultiHopQA, and 0.3061 on MuSiQue, outperforming the strongest baselines on all three benchmarks. Ablations show that replacing the learned controller with a uniform policy costs 3.96–5.78 F1 points, and that additional retrieval is not uniformly beneficial.