We have 6 of 11 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.
This work proposes SkillMaster, a training framework that teaches agents to create new skills, refine existing skills, and select accumulated skills during task solving, and introduces DualAdv-GRPO, which separately estimates advantages for task-solving actions and skill-editing decisions, stabilizing joint training ac...
EnterpriseBench is introduced, a benchmark that evaluates LLM agents across this spectrum, from static question answering to dynamic decision-making, and shows that it provides a practical benchmark for evaluating LLM agents in realistic enterprise strategic reasoning and decision-making.
Libra is presented, which operationalizes the law of large numbers (LLN) as a scaling principle for load balancing: the attention-balancing pool need not grow with the DP degree.
MiniCache is a reusable program caching framework that transforms Program-of-Thought programs into parameterized cache objects, enabling reusable computation across structurally similar requests, and consistently improves the trade-off between inference latency, cache reuse, and task quality.
Outcome-Verified Comparative Self-Distillation (OVCSD) is proposed, which organizes failed student rollouts into a prefix tree, adaptively invokes a skill-conditioned teacher from student-reached states, and retains only outcome-verified successful continuations.
The results suggest that the sweet spot for small models in large-model inference systems lies not in solving complex tasks independently, but in performing lightweight, structured, and verifiable auxiliary operations.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
