AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 10 of 50 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.
Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized interfaces, manipulating scientific objects, and producing verifiable results. We thus introduce OSWorld-Science, a benchmark and evaluation en...
Functional interpretation is introduced, which characterizes an SAE feature as a mapping from its activating input semantics to its output effects under intervention, and Dual-End Agentic Feature Interpretation (DAFI) is presented, an agent that actively gathers evidence and refines input-side, output-side, and functio...
SAEVerbalizer is introduced, a framework that injects SAE decoder directions into an LLM's representations and fine-tunes the LLM's downstream layers to generate natural-language explanations of the injected features.
Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enhancing multi-task reasoning for large language models (LLMs). Our preliminary experiments revealed a phenomenon: SFT suffers from severe task conflicts under multi-stage training, whereas RL enables stable coexi...
This work proposes SurveyReview, a reviewer-aligned, multi-dimensional benchmark and dataset for survey evaluation, and develops a strong baseline evaluator that substantially improves alignment with human reviewers, providing a competitive reference for future research.
RuVerBench is introduced, the first benchmark for assessing LaaJ reliability in rubric verification for agentic scenarios, and the impact of key LaaJ strategies, including prompt design, batching, and majority voting, on rubric verification is analyzed.
The rapid advancement of large language models has transformed survey writing from a months-long manual effort into an automated process. As generation scales, reliable evaluation becomes the bottleneck, and LLMs are increasingly used as survey evaluators. However, existing approaches largely rely on off-the-shelf LLM-...
Tail subtraction is introduced, which removes shared prompt and continuation semantics from boundary states and yields cleaner, more stable steering signals, and suggests that steering depends on representations of what the model is about to do, not merely on what has already appeared.
TrajDebug is proposed, an error-lifecycle tracing framework that addresses long-trajectory error discovery with multi-granularity history compression and evidence-based error identification, and supports critical attribution by tracing each error's resolution status and terminal impact.
DeepWeaver is a novel framework that weaves noisy retrieved evidence into comprehensive answers by maintaining Thought Block Chains (TBCs), a structured representation that groups claims, salient information, keywords, and supporting evidence.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.