Geo News
Community curated by people like you
LatestAICryptoHealthWorld AffairsUS Politics

WorkBuddy Bench — Office Domain stories

Jul 23, 2026

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

A multi-domain evaluation suite for coding agents spanning four work domains — Code, Web, Office, and Security — with contamination-resistant task construction that reverse-engineers tasks from real commits and pull requests, released openly with full task directories, evaluation harness, and reference solutions.

Jul 23, 2026·4 sources
00

Topics

cs.CL – Computation and LanguageAI agentscs.SE – Software EngineeringCoding agentsAI benchmarksSoftware engineeringLLM Leaderboard

Featured Stories

OpenAI pauses development of Astra AI model over critical cybersecurity capability concerns

OpenAI pauses development of Astra AI model over critical cybersecurity capability concerns

Aug 7, 2026·2 sources