8 papers indexed here
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.
Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can fail when their beliefs about environment dynamics are incomplete, incorrect, or outdated. We study a complementary axis of self-evolution: evolving those beliefs durin...
This work studies the challenges of preventing unsafe behavior from persisting and enabling recovery when failures occur through a controlled testbed of stateful authorization tasks, where fixed LLM editors optimize executable agent components and independent traces record their effects.
Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information the question needs, or because the solver fails to use information that is present. We introduce a diagnostic protocol to distinguish these explanations. Using the same so...
Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contributions that are admissible in isolation can jointly enable a prohibited use. Blocking every sensitive action avoids disclosure but defeats the...
These results support a state-based view of robot memory: effective memory for control is not simply retained visual history, but compact task-relevant state derived from the interaction history.
A mechanistic analysis of the VLM model's internal attention patterns shows that a simple describe-then-decide prompting strategy increases vision attention by 30-40% during generation, and task-specific fine-tuning improves dermatology classification but reduces cross-domain medical question-answering performance in t...
Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and committed actions reflect the previous scene. Many simulation robustness benchmarks fix external conditions at reset, leaving this temporal challenge underexamined. We introdu...
Dynamic Hub-and-Spoke Memory is proposed, a training-free framework that represents distant history as structured textual memory while preserving the recent frames as visual tokens for fine-grained perception in streaming video understanding.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
