Share story
AI Science

MCP-Injector preprint introduces controlled failure tests for AI agents

Researchers introduced MCP-Injector, a tool that inserts controlled failures into AI agents' calls to external tools, and reported a 60% drop in task-completion scores under its stress tests. The preprint calibrates failures using 57,240 issue and pull-request threads across 1,774 open-source repositories for the Model Context Protocol, which connects agents to tools. Across a 1,350-cell experiment, task-completion scores fell from 8.08 to 3.23 out of 10. The two tested gpt-oss models, with 20B and 120B parameters, showed no resilience advantage from greater size. Agent frameworks differed in their handling of failures; the tests emphasized permanent failures.
Sources
cs.AI updates on arXiv.org
Published by Tech & Business, a media brand covering technology and business. This story was sourced from cs.AI updates on arXiv.org and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
Capital
Capital

California startups capture record $385B in 2026 funding

California startups have raised a record $385B across seed to growth rounds so far in 2026, representing 75%+ of US startup funding, Crunchbase News reported using Crunchbase data. Early and seed stage companies raised approximate...

Techmeme
Infrastructure
Infrastructure

Sycamine says Japan committed $21 billion to two GlobalFoundries fabs

Japan has committed $21 billion to two GlobalFoundries chip plants in Malta, New York, under an agreement lasting at least 20 years, investment firm Sycamine Capital Management said in a press release. A vehicle co-owned by the US...

Yahoo Finance
AI Products
AI Products

Meta plans $95B stock financing for AI expansion

Meta plans to raise $95B through a stock offering to finance its AI expansion, the Financial Times reports. The financing includes a $35B underwritten equity offering, with Nvidia, AMD and Broadcom set to act as cornerstone invest...

Techmeme
AI Capital
AI Capital

Nous raises $17m to expand household agent beyond Britain

London-based Nous raised $17m to expand its household AI agent outside the UK and add features. Heartcore Capital and existing backer Mosaic Ventures provided funding, with Chalfen Ventures, Joyance Partners and Bain Future Back V...

The Next Web
Capital
Capital

Colare launches hardware hiring tests with $2.5M in pre-seed funding

Colare has launched with $2.5M in pre-seed funding from Afore Capital, Garage Capital and Acadian Ventures, the company said Monday. The San Francisco startup tests hardware engineering candidates through simulations of tasks they...

The Next Web