AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 12 of 35 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.
Language model agents increasingly automate post-training, but when given the full training stack they converge on supervised fine-tuning and spend most effort revising training data. Existing systems give the agent one kind of control, selecting rows from a fixed pool or calling a generator, whereas a human data engin...
Experiments show that the rubric-based rewards reliably distinguish legal responses of different quality and that DPO training on the preference data improves performance across all three dimensions, and Dimension-wise analyses further support the effectiveness of the proposed taxonomy and reward construction.
Downstream RLHF experiments additionally show that using DRM as the training-time reward leads to improved policy performance, directly validating the practical benefit of diffusion-based reward modeling for RLHF training.
This is the first publicly reported autonomous post-training run at this scale, where prior public autonomous-ML-research demonstrations sit at GPT-2-class (~124M) budgets, and is treated as direct, auditable evidence that a scaled autonomous loop can produce discovery, not only optimization.
Results show that simulator-grounded reflection is more reliable than unverified self-revision, while memory anchors agents to early designs and broad tree search explores without converging, pointing to mechanism redesign rather than parameter inference as the central bottleneck.
On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role at the data-minimal limit by training on a single query. One-shot OPD keeps impro...
StudyBench is introduced, a controlled physics benchmark that directly measures how efficiently a self-evolution method converts training material into capability, and turns self-evolution progress from an open-ended pursuit into a measurable target for future research.
This work presents AI4AI\mbox{-}Bench, 10 frozen research repositories spanning 10 training algorithm families, and releases the task suite, the evaluators and every scored submission, so that the measurement can be repeated as these systems change.
Direct On-Policy Distillation (Direct-OPD) is proposed, which transfers the teacher's RL-induced policy shift instead of running sparse-reward RL on the target model and consistently leverages weaker teachers to improve stronger target models.
This work reformulates the implicit reward of sampled-token OPD based on trajectory correctness, then applies a ReLU gating mechanism to ensure that correct trajectories receive non-negative rewards and incorrect ones receive non-positive rewards, making it readily combinable with any policy gradient algorithm, such as...
SWE Refactor Bench is introduced, a benchmark comprising 20 whole-repository migrations, covering 4 kinds of technical debt, and SWE Refactor Bench is positioned as a rigorous testbed for developing coding agents for reliable whole-repository migrations.
Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh, systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.