arXiv Machine Learning
Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 2
Iterative GRPO: Batch-Online Policy Iteration for Multi-Turn RL via Single-Turn RLHF
Iterative GRPO is a batch‑online policy iteration framework that enables multi‑turn reinforcement learning for conversational agents without requiring an interactive user simulator. It alternates between learning a turn‑level Q‑function from logged returns (policy evaluation) and applying single‑turn GRPO against this Q‑function (policy improvement), thereby scoring candidate responses by their expected downstream return. The method is validated on six multi‑turn negotiation environments, demonstrating its practicality for real‑world deployment patterns.
Hugging Face Trending Papers
Jul 8
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-interleaved, which is inefficient for long-horizon agentic tasks.
arXiv AI
Jul 9
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
arXiv:2607. 07508v1 Announce Type: cross Abstract: Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs).
arXiv AI
Jun 3
Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments
arXiv:2606. 03892v1 Announce Type: cross Abstract: Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns.
arXiv AI
Jul 20
Process Reward Informed Tree Rollout for Effective Multi-Turn RL
arXiv:2607. 15610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation.
arXiv AI
Sep 25
Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning
The paper introduces GRAFT, a Graph-based Faithful sTep-level credit-assignment framework that constructs a trajectory graph from rollout trajectories, recovers node state-values via Bellman iteration, and assigns step-level advantages based on node value differences. It also proposes Graph GAE to further reduce state-value estimation bias. Experiments on multi-turn agentic benchmarks demonstrate consistent improvements over GRPO and other recent agentic RL algorithms.