arXiv:2610.17666v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps....
arXiv:2607. 22724v1 Announce Type: cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or steps within a group.
arXiv:2607. 08837v1 Announce Type: cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers.
arXiv:2606. 00135v1 Announce Type: cross Abstract: Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge.
arXiv:2607.08837v4 Announce Type: replace-cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject...
COBALT is a contextual bandit learning method that reuses offline multi-turn code generation trajectories to train large language models efficiently. It treats multi-turn code generation as a one-step recoverable Markov decision process, collecting partial trajectories from a reference LLM and training the target model to complete each partial trajectory in a single step. Experiments on LiveCodeBench show that COBALT improves Pass@1 scores for R1-Distill 8B and Qwen3 8B by up to 9.0 and 6.2 points, matches the performance of two online RL baselines, and enhances robustness against misleading execution feedback.
The paper introduces Coverage-conditioned Group Policy Optimization (CovGPO), a method that addresses sampling imbalance in group-based policy optimization for long-horizon agentic tasks. CovGPO applies first-visit observation coverage only when all samples in a group receive zero outcome reward, giving higher relative advantages to state-exploring actions without altering the original reward signal. Experiments on ALFWorld and WebShop benchmarks demonstrate that CovGPO consistently outperforms group-based baselines, especially on hard tasks.
arXiv:2606. 09961v1 Announce Type: cross Abstract: Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performance in long-horizon tasks.
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:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
HINT-SD introduces a targeted self‑distillation framework for long‑horizon language‑model agents that uses full‑trajectory hindsight to identify failure‑relevant actions and applies feedback‑conditioned distillation only to those action spans. This selective approach reduces the need for per‑turn feedback, improving training efficiency and effectiveness. Experiments on BFCL v3 and AppWorld demonstrate that HINT‑SD outperforms dense per‑turn feedback baselines by up to 13.60 percentage points on average while cutting training time per step by 2.26×.
arXiv:2608.23830v1 Announce Type: cross Abstract: RL has emerged as a powerful paradigm for enhancing the instruction following capabilities of LLMs. While existing training recipes achieve substanti...