←Search results

Search “RAG”

By relevance · Total 306 results Clear search

Wednesday

Thursday

Monday

Thursday

Wednesday

  1. Sarvam AI BlogSelected

    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

    nce 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 e

    Matched fieldsSummary、Body

    #company#Papers/Research#RAG#Agents

Friday

Tuesday

Saturday

Friday

Thursday

Saturday

  1. Cato AI LabsSelected

    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.

    ot 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.

    Matched fieldsSummary、Body

    #research#Safety / alignment#RAG#Microsoft

Sunday

Wednesday

Thursday

  1. Story1 reports · 1 facts

    Sarvam AI introduces a knowledge fabric architecture for enterprise agents

    On October 21, 2026, Sarvam AI introduced a knowledge fabric architecture built for enterprise agents. The architecture consists of two layers, a knowledge tree and a domain ontology, compiling documents once into a structured layer that agents can navigate, query, and cite. According to its published results, 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 using 64% fewer tokens. The knowledge tree is already used in the Sarvam cowork product, while the ontology is built domain by domain and enterprise client by enterprise client.

    nts can navigate, query, and cite. According to its published results, 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 using 64% fewer tokens. The knowledge tree is already used in the Sarvam cowork product, while the ontology is built domain by domain and enterprise client by en

    Matched fieldsSummary

Saturday

  1. Story1 reports · 1 facts

    Aim Labs discloses M365 Copilot zero-click vulnerability EchoLeak

    Aim Labs disclosed the zero-click vulnerability EchoLeak in Microsoft 365 Copilot. An attacker only needs to send the victim one email to exfiltrate sensitive data in the Copilot context without the user's awareness. The attack chain consists of three vulnerabilities, which sequentially 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. Aim Labs said Microsoft has confirmed that no customers were affected.

    lot context without the user's awareness. The attack chain consists of three vulnerabilities, which sequentially 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. Aim Labs said Microsoft has confirmed that no customers were affected.

    Matched fieldsSummary