13 papers
Controlling Tool Use with Heading-Specific Activation Steering
Yuqi Chen, Vincent Siu, Yang Liu +2
Tool-augmented large language models extend their capabilities beyond parametric knowledge through external tools, but tend to invoke them unnecessarily. We investigate whether too…
Peer-Preservation in Frontier Models
Yujin Potter, Nicholas Crispino, Vincent Siu +2
Recent work has found that frontier AI models can exhibit misaligned behaviors in pursuit of assigned goals. We demonstrate that models can also exhibit misaligned behaviors in def…
ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks
Vincent Siu, Manasi Sharma, Dawn Song +3
Computer use agents are evaluated almost exclusively on atomic desktop tasks, but realistic desktop work requires sustaining state across multiple objectives. We study this gap wit…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +306
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents
Pratibha Revankar, Kargi Chauhan, Jihye Kim +3
When LLM agents are coerced into covertly encoding sensitive data (Base64, ROT13, acrostic, synonym chains, and beyond), the resulting outputs evade output-side detection but the u…
Ishigaki-IDS: An Open-Weight Verifier-Aware Model for Information Delivery Specification Drafting in Building Information Modeling
Ryo Kanazawa, Koyo Hidaka, Teppei Miyamoto +9
Building Information Modeling (BIM) projects require information requirements to be described as machine-checkable Information Delivery Specification (IDS) files in order to verify…