Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send the money elsewhere or an order confirmation asks it to reply with a door code. We present BACKDROP, which asks how much of an agent's capability in a clean world survive...
Nusrat Jahan Lia, Shubhashis Roy Dipta· 0 citations
Bengali is the seventh-most-spoken language globally, yet LLM safety evaluation remains overwhelmingly English-centric. We introduce BanglaSafe, a benchmark of 879 Bengali prompts combining 309 natively authored prompts with 570 expert-reviewed prompts, spanning 17 culturally grounded harm categories and five prompting...
Naymul Islam, Nusrat Jahan Lia, Shubhashis Roy Dipta et al.· 1 citation
AgentCheck is presented, an open-source web workbench that turns an MCP server into an intervention surface that makes tool-using LLM failure modes reproducible, comparable, and verifiable before deployment.
Aritra Mazumder, N. J. Lia· arXiv.org· 2 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.