arXiv:2606. 30789v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has become a standard tool for improving the reasoning ability of large language models, yet its training dynamics are still described empirically: reward trajectories are fit with low-parameter functional forms whose constants carry no mechanistic meaning, and hyperparameter choices remain a matter of trial and error.
By Rajat Ghosh, Datta Nimmaturi, Aryan Singhal, Vaishnavi Bhargava, Henry Wong, Johnu George, Debojyoti Dutta
The paper investigates why Group Relative Policy Optimization (GRPO) benefits from per‑prompt normalization by examining the local curvature of the sequence‑level policy gradient. It shows that standard deviation normalization acts as an adaptive gradient, yielding a provably faster convergence rate than unnormalized REINFORCE under mild conditions, with the improvement tied to the average within‑prompt reward standard deviation. The authors also propose IS‑GRPO, an importance‑sampling variant that maintains alignment with the full gradient and offers a tighter convergence guarantee, and empirically validate these theoretical insights on GSM8K and MATH datasets at 1.5B and 7B model scales.
By Cheng Ge, Caitlyn Heqi Yin, Hao Liang, Jiawei Zhang
arXiv:2608. 08770v1 Announce Type: cross Abstract: Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward function.
By Samuel Howard, Nikolas N\"usken
arXiv:2611.05942v1 Announce Type: new
Abstract: RL for LLM reasoning often reaches an early performance plateau as the policy distribution becomes increasingly sharp. Recent work has studied policy e...
By Mengni Jia, Mengyu Zhou, Xiaoxi Jiang, Guanjun Jiang
Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward function. While such rewards are typically defined on individual samples, for many applications it is desirable to steer according to distribution-level rewards, for example to calibrate with population-level information or to encourage diversity.
The paper investigates how enrichment—adding intermediate guidance to sparse rewards in reinforcement learning—affects policy-gradient updates. It shows that omitting or truncating importance-weight corrections implicitly reweights rewards, and decomposes the resulting gradient error into scale, rotation, and variance components. The authors propose a sequential Monte Carlo weight correction that mitigates variance growth, and apply their analysis to a fine-tuned Qwen3-1.7B model on OpenMathReasoning, illustrating how enrichment helps prevent collapse in sparse domains.
By Jinwoo Kim, Shraddha Barke
arXiv:2602. 06014v2 Announce Type: replace-cross Abstract: Thompson sampling (TS) is widely used for stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle.
By Shunxing Yan, Han Zhong
arXiv:2610.25113v3 Announce Type: replace-cross
Abstract: The explore-exploit trade-off is the core problem of reinforcement learning (RL). In its multi-agent, resource-sharing form the optimum is no...
By Galen J. Wilkerson
arXiv:2610.14440v1 Announce Type: cross
Abstract: Asynchronous reinforcement-learning post-training of large language models is computationally efficient but inherently off-policy: the learner update...
By Shayan Mohajer Hamidi, Kayhan Behdin, Wenhui Zhu, Aida Rahmattalabi, Jincheng Cao, Jelena Markovic-Voronov, Alborz Geramifard
arXiv:2608. 01069v1 Announce Type: new Abstract: Bandit algorithms generate data for downstream inference, but adaptive sampling biases post-bandit sample means.
By Lisu Wang, Yilun Chen, Jiaqi Lu
The paper presents a mean‑field framework for studying multi‑agent Q‑learning in networked populations, where agents update stateless Q‑values on a fixed graph while the average behavior of the population feeds back to modify the payoff matrix. A deterministic transport equation for the distribution of Q‑values is derived and coupled with a discrete update for the environmental state, and the model is validated against Monte Carlo simulations on several random graph topologies. Results show that the mean‑field system captures macroscopic cooperation dynamics, that environmental feedback reshapes action‑value ordering, and that the timescale of environmental response critically influences learning outcomes.
By Lichen Wang, Shijia Hua, Linjie Liu
VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion proposes a new inference-time framework that improves steering of frozen masked discrete diffusion models. By reducing the variance of guidance estimates, applying reward tilting to clean-token logits, and adapting the selection temperature at each step, VGAS addresses three default choices in existing pipelines. Experiments on regulatory DNA, protein, and small-molecule benchmarks show that VGAS achieves the best training-free reward performance and matches or surpasses reward-fine-tuned generators.
By Kwanyoung Kim