ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
Actor-curator: Co-adaptive curriculum learning via policy-improvement bandits for rl post-training.arXiv preprint arXiv:2602.20532
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2roles
background 2polarities
background 2representative citing papers
citing papers explorer
-
Learning Agentic Policy from Action Guidance
ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
- CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG