Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Soheil Feizi

Soheil Feizi

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2NLP×1ML×1Crypto×1

Frequent co-authors

Atoosa Chegini1×
Shoumik Saha1×
Kazem Faghih1×

Research Timeline

2026
Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry

This paper demonstrates that the natural language metadata (SKILL.md) used to describe AI agent skills introduces significant semantic supply-chain risks, allowing attackers to manipulate discovery, selection, and governance stages.

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performance comparable to or exceeding complex methods like PRM guided search.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIcs.LGRecentJun 1, 2026

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

Atoosa Chegini, Soheil Feizi

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

View →
cs.AIcs.CRRecentMay 12, 2026

Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry

Shoumik Saha, Kazem Faghih, Soheil Feizi

This paper demonstrates that the natural language metadata (SKILL.md) used to describe AI agent skills introduces significant semantic supply-chain risks, allowing attackers to manipulate discovery, s…

View →