PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
Ranking
Overall
75
Content
80
Popularity
64
Observed public metrics from 1 member.
Merged summary
TL;DR - PATS is an adaptive training scaffold for long-horizon LLM agents that turns recent rollout evidence into task-specific guidance, then removes redundant support as the policy improves. It boosts agent performance while reducing prompt-token usage.
- Converts rollout groups from the latest policy into evidence cards that guide subsequent attempts.
- Dynamically revises or removes guidance to prevent overreliance while preserving rollout diversity.
- Uses standard RLVR with environmental rewards; the scaffold is discarded at deployment.
- Improves ALFWorld and WebShop results by up to 18.6% and uses 32.1% fewer prompt tokens across seven search-augmented QA benchmarks than the baseline.
Sources (1)
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
Public signals
Hugging Face upvotes 1
TL;DR - PATS is an adaptive training scaffold for long-horizon LLM agents that turns recent rollout evidence into task-specific guidance, then removes redundant support as the policy improves. It boosts agent performance while reducing prompt-token usage.
- Converts rollout groups from the latest policy into evidence cards that guide subsequent attempts.
- Dynamically revises or removes guidance to prevent overreliance while preserving rollout diversity.
- Uses standard RLVR with environmental rewards; the scaffold is discarded at deployment.
- Improves ALFWorld and WebShop results by up to 18.6% and uses 32.1% fewer prompt tokens across seven search-augmented QA benchmarks than the baseline.