6 papers
Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub
Fahd Seddik
Agent skills are SKILL.md instructions and scripts that AI coding agents such as Claude Code and Codex run with the permissions of their user. Developers share skills by copying th…
Principled Thoughts for Latent Recursive LLM Systems
Fahd Seddik, Fatemeh Fard
Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between agents, while training supe…
What Makes a Latent Thought Valid? Defining and Auditing Thought Representations in LLMs
Fahd Seddik, Fatemeh Fard
Chain-of-Thought (CoT) reasoning improves the performance of Large Language Models (LLMs), yet it writes steps as text and follows one reasoning path at a time, which limits the ca…
ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localization
Shahd Seddik, Fahd Seddik, Amirrezza Esmaeili +2
Automated program repair at repository scale requires an agent to locate a fault among thousands of files and synthesize a correct patch. Existing graph-based agents represent how…
Panther: Faster and Cheaper Computations with Randomized Numerical Linear Algebra
Fahd Seddik, Abdulrahman Elbedewy, Gaser Sami +2
Training modern deep learning models is increasingly constrained by GPU memory and compute limits. While Randomized Numerical Linear Algebra (RandNLA) offers proven techniques to c…
Analysis of AdvFusion: Adapter-based Multilingual Learning for Code Large Language Models
Amirreza Esmaeili, Fahd Seddik, Yongyi Ji +2
Programming languages can benefit from one another by utilizing a language model for software engineering tasks. Full fine-tuning and Parameter Efficient Fine-Tuning (PEFT) of Code…