4 papers · 1 filter
AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
Christopher Rawles, Sarah Clinckemaillie, Yifan Chang +12
Autonomous agents that execute human tasks by controlling computers can enhance human productivity and application accessibility. However, progress in this field will be driven by…
On the Effects of Data Scale on UI Control Agents
Wei Li, William Bishop, Alice Li +4
Autonomous agents that control computer interfaces to accomplish human tasks are emerging. Leveraging LLMs to power such agents has been of special interest, but unless fine-tuned…
Dissociation of Faithful and Unfaithful Reasoning in LLMs
Evelyn Yee, Alice Li, Chenyu Tang +3
Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how L…
Latent State Estimation Helps UI Agents to Reason
William E Bishop, Alice Li, Christopher Rawles +1
A common problem for agents operating in real-world environments is that the response of an environment to their actions may be non-deterministic and observed through noise. This r…