2 citations · 2 across the 9 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.AI2026
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
Shubham Gandhi, Saurabh Goyal, Kiran Kate +1
Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind settin…
cs.AI2026
Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents
Zidane Wright, Jason Tsay, Anupama Murthi +8
As AI agents move from demos into enterprise deployments, their failure modes become consequential: a misinterpreted tool argument can corrupt production data, a silent reasoning e…