Agents are deployed in applications from trip planners and stock trading to IT incident triage. In most cases, LLM agents work autonomously with minimal rule-based safeguarding, leading to cost and safety issues from irreversible actions. Recent works resolve this either by using a safeguard agent to monitor behavior o...
Babak Barazandeh, C. Swanson, Chinmay Kulkarni et al.· 0 citations
Together, these results recast rank as governing which updates are reachable and what cancellation costs---not how much capacity the model has, which means the smallest rank achieving a desired source--target alignment, is bound.
Localized LoRA-MoE is introduced, a unified framework that fuses localized spatial blocking with dynamic, context-conditioned routing, and decentralized cell-level gating achieves complete statistical parity with an omniscient global coordinator, providing a robust"gradient firewall" that protects surviving pathways fr...
This work reframe trajectory evaluation as a distance between the agent's execution graph and a set of valid solution graphs, and instantiates OTAP via an unbalanced fused Gromov-Wasserstein transport problem over attributed dependency graphs, which is a pseudo-metric that is provably invariant to dependency-preserving...
Babak Barazandeh, Subhabrata Majumdar, G. Michailidis· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
