We have 4 of 6 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
LLM agents now execute tasks end to end with permission to change real systems and increasingly orchestrate subagents that differ in capability and cost. Prior work treats the choice of subagent as an optimization problem. Yet the orchestrator makes this choice from the identities that subagents display, and an attacke...
Results show that preserving already-correct work under unsupported accusation is a distinct safety challenge for long-lived agents, and introduces CAVE-Bench, a benchmark of 365 agentic tasks across six domains built around opaque tasks.
This work proposes Targeted Anti-obfuscation with Mechanistic Enforcement (TAME), which uses Sparse Autoencoders (SAEs) to combine behavioral feedback with targeted suppression of template-associated activations during RL, providing a path from behavioral monitoring to representation-level oversight for more auditable...
The Personal Agent Sycophancy Benchmark (PASB) is introduced, a 1,600-task benchmark that traces whether a conversational claim is accepted, written into durable agent state, and reused in a later neutral query, and shows that agent sycophancy is fundamentally a state-writing governance problem.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
