Mosaic introduces Multi-Session Agentic Reinforcement Learning, allowing trajectories to span an arbitrary number of sessions rather than assuming a single continuous context. It uses critic‑free hierarchical optimization, incorporating session‑usage signals into trajectory‑level advantage estimation and shaping each session’s advantage based on its marginal contribution. Experiments on BrowseComp with Qwen3.5‑4B demonstrate that Mosaic outperforms traditional broadcasting methods in both context compaction and subagent forking, achieving better session utility and allocation while using fewer sessions on average.
arXiv:2607. 05378v1 Announce Type: new Abstract: Long-horizon agentic LLMs are increasingly limited by finite context windows, as extended interaction trajectories can exceed the maximum context length before a task is completed.
Group-Graph Policy Optimization (G2PO) is a novel group-based reinforcement learning algorithm designed for long-horizon agentic tasks. It transforms linear interaction trajectories into a global state‑transition graph, aggregates identical observations across trajectories to reduce sampling variance, and redefines actions as transitions between state nodes. By employing an edge‑centric advantage estimation and globally standardizing TD errors, G2PO identifies and prioritizes critical transitions, achieving up to 22.2% higher success rates than state‑of‑the‑art baselines on benchmarks such as WebShop, ALFWorld, and AppWorld.
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.
The paper introduces CoPE, a method that trains language agents by adding multi‑step action targets to the policy backbone. By supervising each action forecasted from preceding histories, CoPE enables acting and forecasting to co‑evolve without extra inference cost. Across five benchmarks, CoPE outperforms existing RL baselines, achieving up to twice the sample efficiency on ScienceWorld and improving overall performance on realistic applications.
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:2607. 19117v1 Announce Type: new Abstract: Parameterized action reinforcement learning has shown strong performance in environments requiring both discrete action selection and continuous parameterization.
arXiv:2608. 06735v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution.
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:2610.07332v1 Announce Type: new Abstract: Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of agentic behavior and MoE structur...
arXiv:2608. 16798v1 Announce Type: cross Abstract: Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment.
arXiv:2609.13739v1 Announce Type: cross Abstract: Language-model agents are increasingly deployed through diverse harnesses that differ in system prompts, tool schemas, control loops, and trajectory...
arXiv:2606. 02337v1 Announce Type: new Abstract: Constrained Multi-agent reinforcement learning (CMARL) faces two intertwined challenges: the joint action space grows exponentially with the number of agents, and additional requirements couple agents in ways that reward structure alone does not capture.