Skip to main content
Search

# Retrieval-Augmented Generation

54 related articles

Subscribe to updates
  1. arXiv

    Chemists write only the target, and VibeSyn's agents run a ten-step total synthesis: active human input is 7.3%

    A team led by Zhejiang University built VibeSyn, a hierarchical agent system that turns a chemist's molecular objective into synthesis decisions revised as experimental evidence accumulates, then drives computational tools and automated devices to execute them. In a ten-step catharanthine total synthesis the system recorded 722 actions, of which agent reasoning was 69.7% and tool or device outcomes 18.8%, while active human input and human confirmation were 7.3% and 4.2%; starting from 29.8 mmol of 3-ethylpyridine it produced 160 mg of product. Across three campaigns synthesizing cyclic peptides containing unnatural amino acids, active human input and confirmation were 7.5% and 5.2%.

  2. arXiv

    AskALCF assigns each HPC support failure to a component: unattributed turns fall from 41.4% to 14.2% across 2,174

    AskALCF, an agentic system for high-performance computing user support, attributes each failed question-answer turn to one of five components—knowledge, retrieval, prompt, model or tools—instead of returning only a quality score. Across 2,174 production support turns it cut unattributable failures from 41.4% to 14.2%, and on a 150-turn expert reference it raised agreement from 108 to 123 turns. The object of improvement is the rules, prompts and review policy rather than model weights, and experts retain authority over every production-facing change.

  3. Retail media ads stop counting clicks alone: theory-anchored semi-Markov states lift one-step purchase AUC from 0.635 to 0.717

    Retail media networks usually compress clickstreams into click-through, conversion, recency and similar summaries, so two shoppers with identical event counts become indistinguishable. Across three campaign waves on an anonymized omni-channel retailer's platform covering 5.2 million active members, purchase-intention inference is framed as theory-coherent hidden semi-Markov dynamics: states are declared by the Theory of Planned Behavior, the Consumer Decision Journey and the Persuasion Knowledge Model, a retrieval-augmented language model supplies a reference posterior, and a KL regularizer in the expectation step stabilizes state assignment. On n=1,008 paired test consumers the model reaches one-step purchase AUC 0.717 against 0.635 for an action-only covariate baseline.

  4. Chinese Medicine

    A home triage model for TCM gynecology: MAGR-TCM separates emergencies from routine cases in all 30 safety-test records

    For home health consultation and triage in traditional Chinese medicine gynecology, MAGR-TCM turns 741 clinical case records into a knowledge graph of 10,231 entities and 32,051 relationships, then has four specialized agents reason step by step along the disease-pattern-principle-formula-medicinal chain. On 30 held-out test cases its RAGAS faithfulness is 0.821, against 0.766 for GraphRAG, 0.651 for LightRAG and 0.590 for Naive RAG; on a safety set of 10 emergency and 20 routine cases, the red-flag mechanism intercepted and passed every case, with sensitivity and specificity both 1.000. These results come from retrospective, expert-annotated records and have not yet been validated prospectively with real home users.

  5. arXiv

    Retrieval shifts from content to reasoning skeletons: PatternBloom lets a 7B agent compound gains as multi-hop depth grows

    PatternBloom changes the retrieval unit of agentic retrieval-augmented generation from what content to read to how to reason, using typed graph skeletons distilled from high-scoring Stage-I reinforcement-learning trajectories into an external Graph Pattern Memory, then coupling the policy to that frozen memory with a pattern-coverage reward. Across seven QA benchmarks, the 7B version ranks first on EM and F1 on all seven datasets, leads R1-Searcher on average out-of-distribution EM, and the same frozen pattern memory transfers to a Qwen3-8B backbone.

  6. arXiv

    Surgical scene captions learn from retrieved cases: GRAC reaches 52.6% exact instrument-action-target match on EndoVis-18

    GRAC represents a surgical scene as a graph, retrieves graph-caption pairs of similar surgical activities from the training set, and compares instrument-tissue interactions between the current and retrieved scenes to condition caption generation. On the combined EndoVis-18 benchmark it reaches a CIDEr-D of 5.88, against 4.23 for SGT and 3.36 for the strongest conventional Transformer baseline, and an exact instrument-action-target triplet-set accuracy of 52.6%, against 32.7% for SGT and 26.2% for the strongest conventional baseline. On TORS it reaches a CIDEr-D of 5.06, against 3.80 for the strongest baseline.

  7. arXiv

    A finite-sample certificate for which fragments a retrieval corpus should keep, valid even after data-dependent selection

    When a retrieval-augmented generation corpus must be trimmed under a storage or annotation budget, how much query coverage the chosen fragments lose relative to the best feasible set has lacked a finite-sample guarantee that survives data-dependent selection. This work separates selection from auditing: a pilot picks the set, screens competitors and builds a comparison network, then an independent audit acquires relevance labels with probabilities constant within observable strata and yields a simultaneous bound on all retained coverage contrasts, with simulations confirming the nominal level.

  8. LLM-assisted chart review lifts skin-toxicity F1 from 0.77 to 0.88 and cuts reported review time by about a third

    Identifying cutaneous immune-related adverse events (cirAEs) in outpatient notes of patients on immune checkpoint inhibitors has depended on manual chart review, which is slow and inconsistent between reviewers. In a multi-institution study, non-dermatologist reviewers adjudicated with a retrieval-augmented, multi-agent large language model that returned a binary recommendation plus the supporting note excerpts. Against ground truth from an oncodermatologist, the assisted group reached F1 0.88 and Cohen's κ 0.82 versus 0.77 and 0.50 for manual review, and reviewers self-reported a drop from 15 to 10 minutes per chart.

  9. Retrieval-augmented generation gets three separately optimized agents: TRIO splits query expansion, retrieval judging and answering

    Retrieval-augmented generation (RAG), which fetches external material before a language model answers, often falters on weak retrieval and fabricated content. TRIO splits that pipeline into three agents, for query expansion, for judging whether retrieval is sufficient, and for answering, and lets each improve iteratively under its own reward signal: the expansion agent is rewarded by gains in answer quality, the judge agent is supervised by unanimity-voted sufficiency labels, and the answer agent trains with dynamic matching-based rewards plus curriculum learning. Experiments across multiple benchmark datasets report TRIO as more effective than state-of-the-art approaches, and the code is public.

  10. GraphCLaRa adds a graph reranker ahead of a frozen CLaRa reader: up to 6.6 F1 gain on multihop QA with fewer documents

    Retrieval-augmented multihop question answering suffers from noisy context, and CLaRa's compression of retrieved documents into dense latent memory makes the structural relations between documents harder to exploit. GraphCLaRa places a roughly 1.3M-parameter graph reranker before the frozen CLaRa reader: it builds a query-aware document graph, propagates evidence with a graph attention network, and adaptively decides how many documents to pass on. Across four QA benchmarks it raises answer F1 on three, by 6.6 on 2Wiki, 6.4 on MuSiQue and 2.5 on NQ, while using fewer documents, and trails by 1.1 F1 on the retrieval-saturated HotpotQA.