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

Sambit Sahu

2 indexed papers

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

Publications per year

2
26

Top categories

AI×2Crypto×1

Frequent co-authors

Chenyang Zhu1×
Jiayu Yao1×
Kushal Chawla1×
Youbing Yin1×
Nathan Wolfe1×
Pengshan Cai1×

Research Timeline

2026
CoT-Guard: Small Models for Strong Monitoring

The paper introduces CoT-Guard, a small, cost-effective 4B-parameter model that significantly outperforms large, expensive monitors like GPT-5 in detecting hidden objectives in code generation tasks.

SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation

SAFARI is a framework that decouples diagnostic accuracy from context limits in autonomous agents by equipping them with a toolbox to read and search trajectory segments and a persistent STM for cross-turn reasoning.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentJun 23, 2026

SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation

Chenyang Zhu, Jiayu Yao, Kushal Chawla, Youbing Yin +9 more

SAFARI is a framework that decouples diagnostic accuracy from context limits in autonomous agents by equipping them with a toolbox to read and search trajectory segments and a persistent STM for cross…

View →
cs.CRcs.AIRecentMay 12, 2026

CoT-Guard: Small Models for Strong Monitoring

Nirav Diwan, Han Wang, Berkcan Kapusuzoglu, Ramin Moradi +5 more

The paper introduces CoT-Guard, a small, cost-effective 4B-parameter model that significantly outperforms large, expensive monitors like GPT-5 in detecting hidden objectives in code generation tasks.

View →