Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback. We introduce Banzhaf Resource Attribution (BRA), a controlled factorial framework that measures each resource's marginal contribution to repair...
Saiyue Lyu, Jerrold Huang, Yun-Bei Zhang et al.· 0 citations
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.
Yun-Bei Zhang, Janet Wang, Saiyue Lyu et al.· 1 citation
VersE, a Verified Self-Evolving optimizer for agent harnesses, improves all four evaluated harness optimizers on held-out SWE-rebench tasks and newer out-of-distribution tasks in five languages.
Ze-Kai Wang, Ying-Qiang Ge, Ze-Kun Wang et al.· 2 citations
This work introduces authorization-paired evaluation, which makes blocking prohibited uses and completing required authorized uses a joint success criterion, and FlowReview, a framework connecting object resolution, permission ranking, and deterministic enforcement, which establishes a system-level requirement for mult...
Yun-Bei Zhang, Saiyue Lyu, Janet Wang et al.· 0 citations
The main idea is to use all the negative samples when optimizing the learning objective to avoid the sampling process, and rearrange the origin loss function into a linear form and take advantage of meticulous mathematical derivation to reduce the complexity of the loss function.
Pierpaolo Basile, Birgitta Dresp-Langley, Jianchao Ji et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.