2 citations · 3 across the 11 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.IR2026
Advertising to Agents: Measuring Description-Framing Bias in LLM Tool Selection
Haochuan Kevin Wang, Zechen Zhang
AI agents often pick tools from registries, where each provider writes its tool's description; we ask whether sales language there changes which tool an agent picks. We built pairs…
cs.CR2026
Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Five Production LLMs
Haochuan Kevin Wang, Zechen Zhang
Multi-agent LLM systems now read documents, web pages and tool results on behalf of users, yet their resistance to prompt injection is usually reported as one number: did the attac…
cs.LG2026
Same Pieces, Different Servers: A Tetris Benchmark for AI Agents as Served
Haochuan Wang, Haochuan Kevin Wang
An agent meets a model as served: through an endpoint with a price card, a shared cache and other tenants, or on whatever hardware a self-hosted model runs. Benchmarks rank the wei…