Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs

Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study of RLVR's distributional effects organized around three main analyses: (1) token-level characterization of distributional shifts between base and RL models, (2) the impact of token-level distributional shifts on sequence-level reasoning performance through cross-sampling interventions, and (3) fine-grained mechanics of these shifts at the token level. We find that RL fine-tuning induces highly sparse and targeted changes, with only a small fraction of token distributions exhibiting meaningful divergence between the base and RL policies. We further characterize the structure and evolution of these shifts through analyses of token entropy, positional concentration, and reallocation of probability mass. To assess the functional importance of these sparse changes, we conduct cross-sampling experiments that selectively swap token choices between the base and RL models with varying intervention budgets. We show that inserting only a small fraction of RL-sampled tokens into base generations progressively recovers RL performance gains, while injecting a similarly small number of base token choices into otherwise RL-generated sequences collapses performance to base levels, isolating a small set of token-level decisions directly responsible for RLVR's performance gains. Finally, we explore divergence-weighted variants of the advantage signal as a diagnostic intervention, finding that they can yield improvements over baselines. Together, our results shed light on the distributional changes induced by RLVR and provide a fine-grained, token-level lens for understanding RLVR fine-tuning as a targeted refinement process.

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the \textbf{magnitude} of these updates, largely overlooking their \textbf{direction}. In this work, we argue that the direction of updates is a more critical lens for understanding RLVR's effects, which can be captured by the signed, token-level log probability difference $Δ\log p$ between the base and final RLVR models. Through statistical analysis and token-replacement interventions, we demonstrate that $Δ\log p$ more effectively identifies sparse, yet reasoning-critical updates than magnitude-based metrics (\eg divergence or entropy). Building on this insight, we propose two practical applications: (1) a \textit{test-time extrapolation} method that amplifies the policy along the learned $Δ\log p$ direction to improve reasoning accuracy without further training; (2) a \textit{training-time reweighting} method that focuses learning on low-probability (corresponding to higher $Δ\log p$) tokens, which improves reasoning performance across models and benchmarks. Our work establishes the direction of change as a key principle for analyzing and improving RLVR.

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style training scales effectively, it typically relies on outcome-based rewards (ORM) that distribute a global advantage uniformly across every token in a trajectory. We argue that this coarse-grained credit assignment imposes a performance ceiling by failing to distinguish critical logical pivots from trivial tokens. FIPO addresses this by incorporating discounted future-KL divergence into the policy update, creating a dense advantage formulation that re-weights tokens based on their influence on subsequent trajectory behavior. Empirically, FIPO enables models to break through the length stagnation seen in standard baselines. Evaluated on Qwen2.5-32B, FIPO extends the average chain-of-thought length from roughly 4,000 to over 10,000 tokens and increases AIME 2024 Pass@1 accuracy from 50.0% to a peak of 58.0% (converging at approximately 56.0\%). This outperforms both DeepSeek-R1-Zero-Math-32B (around 47.0%) and o1-mini (approximately 56.0%). Our results suggest that establishing dense advantage formulations is a vital path for evolving ORM-based algorithms to unlock the full reasoning potential of base models. We open-source our training system, built on the verl framework.

Assessing Markov Property in Driving Behaviors: Insights from Statistical Tests

The Markov property serves as a foundational assumption in most existing work on vehicle driving behavior, positing that future states depend solely on the current state, not the series of preceding states. This study validates the Markov properties of vehicle trajectories for both Autonomous Vehicles (AVs) and Human-driven Vehicles (HVs). A statistical method used to test whether time series data exhibits Markov properties is applied to examine whether the trajectory data possesses Markov characteristics. t test and F test are additionally introduced to characterize the differences in Markov properties between AVs and HVs. Based on two public trajectory datasets, we investigate the presence and order of the Markov property of different types of vehicles through rigorous statistical tests. Our findings reveal that AV trajectories generally exhibit stronger Markov properties compared to HV trajectories, with a higher percentage conforming to the Markov property and lower Markov orders. In contrast, HV trajectories display greater variability and heterogeneity in decision-making processes, reflecting the complex perception and information processing involved in human driving. These results have significant implications for the development of driving behavior models, AV controllers, and traffic simulation systems. Our study also demonstrates the feasibility of using statistical methods to test the presence of Markov properties in driving trajectory data.

Transformer Alignment in Large Language Models

Large Language Models (LLMs) have made significant strides in natural language processing, and a precise understanding of the internal mechanisms driving their success is essential. We regard LLMs as transforming embeddings via a discrete, coupled, nonlinear, dynamical system in high dimensions. This perspective motivates tracing the trajectories of individual tokens as they pass through transformer blocks, and linearizing the system along these trajectories through their Jacobian matrices. In our analysis of 38 openly available LLMs, we uncover the alignment of top left and right singular vectors of Residual Jacobians, as well as the emergence of linearity and layer-wise exponential growth. Notably, we discover that increased alignment $\textit{positively correlates}$ with model performance. Metrics evaluated post-training show significant improvement in comparison to measurements made with randomly initialized weights, highlighting the significant effects of training in transformers. These findings reveal a remarkable level of regularity that has previously been overlooked, reinforcing the dynamical interpretation and paving the way for deeper understanding and optimization of LLM architectures.

Pushing Boundaries: Mixup's Influence on Neural Collapse

Mixup is a data augmentation strategy that employs convex combinations of training instances and their respective labels to augment the robustness and calibration of deep neural networks. Despite its widespread adoption, the nuanced mechanisms that underpin its success are not entirely understood. The observed phenomenon of Neural Collapse, where the last-layer activations and classifier of deep networks converge to a simplex equiangular tight frame (ETF), provides a compelling motivation to explore whether mixup induces alternative geometric configurations and whether those could explain its success. In this study, we delve into the last-layer activations of training data for deep networks subjected to mixup, aiming to uncover insights into its operational efficacy. Our investigation, spanning various architectures and dataset pairs, reveals that mixup's last-layer activations predominantly converge to a distinctive configuration different than one might expect. In this configuration, activations from mixed-up examples of identical classes align with the classifier, while those from different classes delineate channels along the decision boundary. Moreover, activations in earlier layers exhibit patterns, as if trained with manifold mixup. These findings are unexpected, as mixed-up features are not simple convex combinations of feature class means (as one might get, for example, by training mixup with the mean squared error loss). By analyzing this distinctive geometric configuration, we elucidate the mechanisms by which mixup enhances model calibration. To further validate our empirical observations, we conduct a theoretical analysis under the assumption of an unconstrained features model, utilizing the mixup loss. Through this, we characterize and derive the optimal last-layer features under the assumption that the classifier forms a simplex ETF.

Beyond Text: Improving LLM's Decision Making for Robot Navigation via Vocal Cues

This work highlights a critical shortcoming in text-based Large Language Models (LLMs) used for human-robot interaction, demonstrating that text alone as a conversation modality falls short in such applications. While LLMs excel in processing text in these human conversations, they struggle with the nuances of verbal instructions in scenarios like social navigation, where ambiguity and uncertainty can erode trust in robotic and other AI systems. We can address this shortcoming by moving beyond text and additionally focusing on the paralinguistic features of these audio responses. These features are the aspects of spoken communication that do not involve the literal wording (lexical content) but convey meaning and nuance through how something is said. We present "Beyond Text"; an approach that improves LLM decision-making by integrating audio transcription along with a subsection of these features, which focus on the affect and more relevant in human-robot conversations. This approach not only achieves a 70.26% winning rate, outperforming existing LLMs by 48.30%, but also enhances robustness against token manipulation adversarial attacks, highlighted by a 22.44% less decrease ratio than the text-only language model in winning rate. "Beyond Text" marks an advancement in social robot navigation and broader Human-Robot interactions, seamlessly integrating text-based guidance with human-audio-informed language models.