SPO++ is a new reinforcement learning method that eliminates the need for waiting on sibling rollouts by using a persistent prompt-level value estimate. It corrects a mismatch in the original SPO approach by standardizing terminal-outcome advantages under an action-token measure and reorganizes prompt evidence based on the policy event that generated it. Experiments on ALFWorld and Math‑TIR show that SPO++ improves online learning efficiency, with action-token-measure normalization identified as the key component.
arXiv:2608. 07118v1 Announce Type: new Abstract: Credit assignment in multi-turn agent reinforcement learning operates at two levels: assigning trajectory-level credit to actions and distributing each action's credit across its tokens.
The paper introduces Potential-Guided Policy Optimization (PGPO), a method for multi-turn agentic tasks that improves credit assignment by estimating empirical state potentials from anchor-state-group return statistics. PGPO derives action advantages from potential differences between adjacent states, enabling cross-trajectory credit propagation and finer-grained step-level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop demonstrate strong performance compared to recent group-based reinforcement learning methods, with negligible training overhead.
arXiv:2605. 13217v1 Announce Type: cross Abstract: Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge.
PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks proposes a new reinforcement learning approach that estimates empirical state potentials from anchor-state-group return statistics within each rollout group. By deriving action advantages from potential differences between adjacent states, PGPO enables cross‑trajectory credit propagation, providing finer‑grained step‑level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop demonstrate strong overall performance compared to recent group‑based RL methods, with negligible training overhead.
arXiv:2610.00388v1 Announce Type: cross Abstract: Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However,...
arXiv:2608. 19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models.
Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy advantages from multiple rollouts, avoiding the substantial memory overhead of conventional proximal policy optimization (PPO) and achieving strong performance on long-horizon interactive tasks.
arXiv:2607. 04242v1 Announce Type: new Abstract: Group-based reinforcement learning (RL) has become an effective paradigm for improving large language model agents on long-horizon interactive tasks.
arXiv:2607. 27973v1 Announce Type: new Abstract: Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents.
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.
arXiv:2609.36864v1 Announce Type: new Abstract: Group-relative methods for reinforcement learning with verifiable rewards (RLVR) learn from differences in rollout outcomes. Independently sampling com...
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.