AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
12 papers indexed here
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 attempts to make use of high-quality public documents with small perturbations and empirically finds that LLMs can successfully generate context-dependent reasoning traces and answers, which are then used to train a student model that substantially improves the performance on CL-bench.
Executable environments are critical for post-training agents on tasks that require tool use and multi-step interaction, but constructing executable tasks together with their environments remains difficult to scale. Skills provide reusable domain knowledge, operational procedures, and tool-use instructions, but a subst...
This work introduces Compositional Environment Scaling (\textbf{CompoWorld}), which expands the task space by composing a finite library of reusable services, and guides reinforcement learning toward full task completion by emphasizing criteria with lower pass rates within each rollout group.
Policy Aligned Critic Training (PACT), which adopts an Actor-then-Critic update order to apply importance sampling correction to critic training and better align the critic with the updated policy, is developed.
RedKnot establishes a new foundation for AI infrastructure by transforming the KV cache from a monolithic, passive runtime artifact into a dynamic, model-aware runtime substrate for scalable LLM serving.
The proposed OneModel, a unified framework for multi-stream final ranking, maps heterogeneous behaviors into shared event sequences, learns long-context user representations with an action-oriented backbone, and introduces scenario-aware Information Modulation to balance cross-stream transfer and stream-specific specia...
Experiments show that \textsc{AtomRec} consistently outperforms state-of-the-art agentic and memory-augmented baselines, with around 8.5\% average relative improvement across metrics.
This work presents a DeepSeek-V4 realization of RedKnot's head-aware reuse principle, a DeepSeek-V4 realization of RedKnot's head-aware reuse principle, and describes the factorization, position repair, token-row closure, sparse-MoE support, TP8 integration, and the measurement boundaries needed to interpret these resu...
This work presents Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe behind them, and plans to release the model weights together with the complete recipe for data construction, training, and evaluation.
PILOT is presented, a supervisor-worker harness for live self-improvement through two coupled mechanisms: (1) live steering lets a separate supervisor redirect or abort the active worker during execution; and (2) live self-evolution distils procedures and failure modes revealed during execution into reusable skills and...
To further optimize the reasoning trajectory, HiLaR combines final recommendation feedback with layer-aware process rewards derived from the marginal target-likelihood gain of each state, and generally outperforms strong sequential, generative, and LLM-based recommendation baselines.
This work proposes Akashic, a low-overhead memory system built around MemAttention, which organizes context into bounded chunks and models semantic relationships across chunks, preserving cross-chunk evidence without repeatedly rewriting the full history.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.