activity
20232026
most citedBadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

2 citations · 4 across the 8 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CL2026

HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution

Xiaotian Luo, Dizhan Xue, Fengxingyu Wang +2

Large Language Models (LLMs) have enabled capable agents across diverse applications. Beyond the foundation model, the performance of an agent is governed by the surrounding agent…