Showing 2026Show all
3 papers · 1 filter
cs.CL2026
Before the Rollout Ends: Early Terminal Reward Prediction for Long-horizon Coding Agents
Jihan Yao, Sihan Zeng, Shangbin Feng +3
Long-horizon coding agents receive verifiable rewards only after completing expensive sequences of tool calls. This increases inference cost, amplifies early wrong hypotheses, and…
cs.LG2026
Rethinking Neural Network Learning Rates: A Stackelberg Perspective
Sihan Zeng, Sujay Bhatt, Sumitra Ganesh
Neural networks are typically trained with a single learning rate across all layers. While recent empirical evidence suggests that assigning layer-specific learning rates can accel…
cs.LG2026
A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning
Sihan Zeng, Sujay Bhatt, Sumitra Ganesh +1
We study a structured bi-level optimization problem where the upper-level objective is a smooth function and the lower-level problem is policy optimization in a Markov decision pro…