Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memory
Jayant Parashar, Eugene F. Douglass, William C. Bastian +1
An agent harness controls how a language model accesses information, uses tools, preserves memory, and checks its work. Improving this software is costly when each evaluation requi…
cs.AI2026
KACE: Knowledge-Adaptive Context Engineering for Mathematical Reasoning
Jayant Parashar, Suchendra M. Bhandarkar
Context-engineering methods improve a frozen language model by learning text from execution feedback and placing it in the prompt. When one learned prompt carries everything that w…