Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Learning
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 p
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Lea” ≈ “AgentCore-8B””
- FuzzySimilar title/name (fuzzy) · 87%SWE-agent/SWE-agent →
“Fuzzy title match (0.94): “Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Lea” ≈ “SWE-agent/SWE-agent””
- FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent →
“Fuzzy title match (0.94): “Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Lea” ≈ “zhayujie/CowAgent””
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzySimilar title/name (fuzzy) · 59%NousResearch/hermes-agent →
“Fuzzy title match (0.73): “Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Lea” ≈ “NousResearch/hermes-agent””
- LinkedLinked via arxiv author · 85%Zixuan Wang →
“Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Learning”
- LinkedLinked via arxiv author · 85%Yanrui Miao →
“Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Learning”