Agent-G^2: Gaussian Guidance for Agentic Reinforcement Learning
Abstract
Agent-G² models hint depth as a Gaussian distribution estimated online from existing rollouts, improving reinforcement learning on long-horizon tasks without extra probing.
Hint-based reinforcement learning addresses reward sparsity in long-horizon agentic tasks by retaining a prefix of an expert trajectory before each rollout, letting the policy explore from a state closer to success. Its effectiveness hinges on the guidance depth: how much of the trajectory to keep. Existing methods treat this depth as a deterministic scalar. Scheduled approaches share one value across samples and ignore per-task heterogeneity; per-sample probing estimates it separately at the cost of extra rollouts. We find that useful guidance occupies a band of depths whose informativeness profile is approximately Gaussian around the band center, rather than concentrating at a single optimal point. We propose Agent-G^2, a Gaussian guidance framework that draws the depth per task from a Gaussian whose center and spread are estimated online from rollouts already collected for policy optimization, requiring no probe rollouts or learned depth predictor. The center combines a global baseline with per-cluster difficulty, and the spread tracks within-cluster variance. We evaluate Agent-G^2 on ALFWorld and WebShop on Qwen2.5-1.5B / 7B-Instruct. Agent-G^2 outperforms the strongest hint-based, hint-free, and Aux-RL baselines on ALFWorld by 2.3 / 3.9 / 7.4 points at under one-third the rollout cost of per-sample probing.
Get this paper in your agent:
hf papers read 2608.23318 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 4
xiamoent/Agent-G2-alfworld-7b
Datasets citing this paper 1
xiamoent/Agent-G2-ALFWorld-Webshop-sft-data
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper