←RAG
← All topics

RAG

Retrieval-augmented generation, knowledge bases, search and context engineering.

Public reading groups
25
Last 30 days
10
Directory status
Curated topic

LatestSarvam AI releases enterprise agent knowledge fabric architecture and benchmark results

Latest reading groups

Duplicate reports of the same fact are grouped

  1. Sarvam AI BlogFirst-partyResearch
    AI score61

    Sarvam AI releases enterprise agent knowledge fabric architecture and benchmark results

    Sarvam AI introduced a knowledge fabric built for enterprise agents, composed of two layers, a knowledge tree and a domain ontology, which compiles documents once into a structured layer that agents can navigate, query, and cite. On the Harvey LAB benchmark, answers using GLM 5.3 met 84.2% of expert grading criteria, higher than agentic RAG's 55.1%, with average task cost dropping from $0.64 to $0.28; on Sierra's tau-knowledge banking benchmark, it achieved accuracy comparable to the baseline with 64% fewer tokens. The knowledge tree is already used in the Sarvam cowork product, while the ontology is built domain by domain and enterprise customer by enterprise customer.

    How we built the knowledge fabric for enterprise agents

    Why read thisSarvam AI has disclosed the architecture of the knowledge fabric and multiple benchmark comparisons, so readers can judge the trade-offs of the structured knowledge layer relative to traditional RAG.

  1. Cohere Product and Research BlogFirst-partyProduct release
    AI score63

    Cohere releases Rerank 5 Pro and Fast retrieval models

    Cohere releases enterprise retrieval model Rerank 5, in Pro and Fast tiers, now available on Cohere API, Model Vault, Microsoft Foundry and Amazon SageMaker, with Pro priced at $0.05 per 1M tokens and Fast at $0.02. Cohere says Rerank 5 Pro leads all tested models on four public benchmarks: ViDoRe V3, nanoMTEB, BRIGHT and BEIR, ranking first on 39 of 46 composite datasets. The new Context Focus feature can return the most relevant text snippets within a document in a single call; in official tests, removing half the context lost only 2 percentage points of answer quality.

    Abstract image

    Why read thisThe original text provides the benchmark performance of Rerank 5, the token savings and calibration scores of Context Focus, from which the impact of the retrieval layer on RAG and agent costs can be judged.

  1. Aravind SrinivasModel releases
    AI score66

    Gemini 4 Argon Sets New SoTA on the WANDR Benchmark and Launches on Perplexity

    Perplexity CEO Aravind Srinivas said that Gemini 4 Argon is a frontier model that has set a new SoTA on the Wide-And-Deep-Research (WANDR) benchmark, and it is now available to all Perplexity users, covering fast search and the Computer agent mode. Perplexity's official account previously said that the model set a new record on WANDR and was offered to Pro and Max subscribers.

    Why read thisPerplexity has integrated Gemini 4 Argon and made it available to all users; readers can learn about the model's performance on deep research benchmarks and its availability.

  1. Cato AI LabsFirst-partyResearch
    AI score81

    Aim Labs discloses the complete attack chain of the M365 Copilot zero-click vulnerability EchoLeak

    Aim Labs disclosed the zero-click vulnerability EchoLeak in Microsoft 365 Copilot: an attacker only needs to send a single email to the victim to exfiltrate sensitive data in the Copilot context without the user's awareness. The attack chain consists of three vulnerabilities, which in sequence bypass the XPIA prompt injection classifier, the sanitization of external links and images, and, with the help of SharePoint and Teams URLs, bypass CSP restrictions. Aim Labs calls the core technique LLM Scope Violation and believes that similar design flaws may also exist in other RAG-based chatbots and AI agents, and states that Microsoft has confirmed that no customers were affected.

    Why read thisAim Labs broke down the zero-click data exfiltration chain of M365 Copilot and provided protection ideas that can be transferred to other RAG applications.