AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 7 of 19 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.
EviGraph is presented, a deep-search framework that separates search execution from evidence recording while using a shared policy for the trainable roles, enabling reinforcement learning to directly supervise evidence construction rather than only the final answer.
DUET is proposed, a token-selective on-policy distillation method for prohibition compliance that achieves 72.3-85.2% violation compliance while preserving 88-93% normal utility, dramatically outperforming teacher model and other distillation baselines.
This work introduces SocialBuddy, the first agentic search framework tailored for social scenarios, and constructs SocialEnv, the first large-scale simulated environment for social search, which delivers multi-scale guidance in complex long-sequence scenarios.
Knowledge-base construction and querying are typically optimized in isolation: retrieval-augmented agents operate over a fixed, externally maintained index, whereas construction receives no signal from downstream use. We present WikiLoop, a feedback-coupled framework that jointly learns to build and navigate an agent-n...
The results establish history reliability as a distinct tool-use bottleneck and demonstrate reliable-state policy transfer as an effective and scalable solution.
Influence-Aware Policy Optimization (IAPO), which represents each rollout as a typed influence-dependency graph over trainable agent actions, with user and tool observations serving as evidence, is introduced and advances the understanding of credit assignment in multi-turn user interactions.
Semantic Flow Regularization (SFR), a lightweight auxiliary objective that supervises the backbone with continuous sentence-encoder embeddings of future segments via conditional flow matching, improves output diversity, style fidelity, and response quality over SFT on a large-scale industrial dialogue dataset.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.