Latest

Every published item, in order · 7652 items
Oct 16
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
PapersBuildersMulti-sourceSelected11:32
MLExpert: 35B Agentic Model for Autonomous Machine Learning Engineering

A 35B model matching frontier-scale systems on MLE-Bench Lite suggests agentic MLE performance depends more on training method than raw parameter count, lowering the hardware bar for teams building autonomous experimentation agents. The WIRL reward design over multi-turn execution windows is a reusable recipe for anyone training long-horizon agents beyond ML engineering. The paper also ships an executable task factory, so practitioners can adapt the harness to their own domains.

Event
arXiv cs.LG@Shangheng Du et al. (10)Source
PapersPolicyMulti-sourceSelected11:27
MCP-FSD Uncovers Filesystem Capability Laundering in MCP Servers

Client-side tool approval in MCP grants the whole server process broad filesystem access, so a tool approved for one operation can exfiltrate credentials the contract never mentions. Security engineers running local agent stacks should audit installed MCP servers and enforce sandbox boundaries rather than trusting declared tool schemas. The two CVEs in Anthropic's Git MCP Server make this a concrete patch item for anyone using that server.

Event
arXiv: Anthropic@Zeqian Huang et al. (5)Source

Only the latest 2000 items are listed; for older ones see the daily archive