Policy optimization (PO) for Large Language Models faces a stability--exploration trade-off, currently mediated by an action-side Policy-KL regularizer. This puts practitioners in a double bind: keepi...
arXiv:2607. 10481v1 Announce Type: cross Abstract: Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), yet the training process remains notoriously fragile.
arXiv:2602. 04879v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm.
arXiv:2605. 25582v2 Announce Type: replace Abstract: Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories after a single update, while off-policy reuse introduces distribution mismatch that existing trust-region techniques mitigate primarily by enforcing conservative optimization, often leaving rich training signals underutilized.
The paper investigates how different estimators of the reverse Kullback–Leibler (KL) divergence used as a regularization term in reinforcement learning (RL) training of large language models (LLMs) affect training stability and downstream performance. By analyzing gradient bias across various estimator configurations, the authors demonstrate that biased gradients can cause training instabilities, while unbiased configurations improve performance on both in‑domain and out‑of‑domain tasks. Experiments on Qwen2.5‑7B, Llama‑3.1‑8B‑Instruct, and Qwen3‑4B‑Instruct‑2507 confirm these findings and show that KL regularization also stabilizes off‑policy RL training in asynchronous setups.
arXiv:2607. 06987v1 Announce Type: new Abstract: Reinforcement learning (RL) has become the standard paradigm for enhancing the complex reasoning capabilities of large language models (LLMs).
The paper introduces Drift-Constrained Optimization (DCO), a framework that treats behavioral drift during fine‑tuning of instruction models as a bounded constraint rather than an uncontrolled side effect. By defining a drift budget, the authors reformulate fine‑tuning as a direction‑selection problem, showing that choosing different update directions can qualitatively change outcomes. Experiments on Qwen3 models demonstrate that carefully selected directions improve scientific reasoning and multilingual translation while preserving reasoning capabilities and general performance.
arXiv:2603.16157v2 Announce Type: replace-cross Abstract: While Reinforcement Learning (RL) enhances Large Language Model reasoning, on-policy algorithms like GRPO are sample-inefficient as they disc...
Gibbs‑Gap Policy Optimization (GGPO) is a new off‑policy reinforcement learning method that avoids high‑variance learner‑to‑behavior importance weights by minimizing a log‑mean‑exp contrast of KL‑adjusted rewards across responses to the same prompt. Derived from KL‑regularized policy optimization, GGPO guarantees that a learner’s single‑response expected reward is at least the behavior policy’s best‑of‑K reward minus bounded terms, and it includes a reference‑refresh mechanism that empirically improves performance. Experiments on benchmark problems and mathematical reasoning tasks show GGPO outperforming GRPO and AGRO, especially under training‑inference mismatch and with fixed offline data. whyItMatters":"The paper demonstrates a practical improvement in off‑policy RL for language models by reducing variance and ensuring better reward guarantees, which is directly supported by the reported empirical gains and theoretical bounds."
The paper introduces Feedback‑Enriched Environments (FEEs) as a new approach to training large language models as autonomous agents for long‑horizon tasks. By shifting from action guidance to observation enrichment during later stages of exploration, FEEs improve performance across SciWorld and BFCL benchmarks with various Qwen3 model scales and RL algorithms. The study shows that FEEs stabilize training, promote proactive exploration, embed environmental guidance into policy weights, and highlight intra‑group feedback consistency as key for stable optimization.
The paper introduces SORL, a framework that stabilizes off‑policy reinforcement learning for long‑horizon large language model agents. It identifies two key instability sources—token‑level policy granularity mismatches and high‑variance off‑policy updates—and proposes turn‑level importance sampling and clipping‑triggered normalization to align optimization with multi‑turn interactions. Two instantiations, SO‑PPO and SO‑GRPO, are evaluated on open‑domain, multi‑hop, and medical QA benchmarks, as well as on asynchronous RL for mathematical reasoning, showing improved robustness without the need for early stopping or heuristic tuning.
arXiv:2608. 09805v1 Announce Type: cross Abstract: Exploration has been a focus of reinforcement learning research for a long time.