Adaptive algorithms increasingly make decisions while reshaping the dynamics that generate their future data. We establish a shrinking-tube concentration bound for projected stochastic approximation driven by an adaptive Markov chain. The bound guarantees, with high probability, that every iterate after a chosen time r...
The findings connect authority information, effect admission, and infrastructure reuse in stateful agents to connect authority information, effect admission, and infrastructure reuse in stateful agents.
Yang Li, Zong-Si Xu, Sergey Volkov et al.· 0 citations
Terminal utility evaluates a complete agentic workflow, but learning requires credit for the decisions within it. We introduce Attentive Search over Counterfactual Trees (ASCT), a framework that turns training-time multi-step search into local action credit. At actor-visited states, an auxiliary tree evaluates alternat...
Yang Li, Jin-Han Yang, Hai Liu et al.· 0 citations
This work introduces Agent-UCT, a tree search algorithm that extends UCT with a reuse-aware regularization term derived from a bipartite prefix reuse graph, and RAGSpace, a unified framework for cost-aware, reproducible, and compositionally efficient agentic workflow optimization.
Yang Li, Hai Liu, Dian Shao 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.
