Abstract:Reinforcement Learning from Human Feedback (RLHF) has emerged as a critical technique for training large language models. However, reward hacking-a phenomenon where models exploit flaws in the reward model-remains a significant barrier to achieving robust and scalable intelligence through long-term training. Existing studies have proposed uncertain reward model to address reward hacking, however, they often lack systematic or theoretical foundations, failing to model the uncertainty intrinsically emerging from preference data. In this paper, we propose the Probabilistic Uncertain Reward Model (PURM), a natural generalization of the classical Bradley-Terry reward model. PURM learns reward distributions directly from preference data and quantifies per-sample uncertainty via the average overlap area between reward distributions. To mitigate reward hacking, we further introduce an uncertainty-aware penalty into Proximal Policy Optimization (PPO), which leverages the learned uncertainty to dynamically balance reward optimization and exploration. We propose a lightweight and easy-to-use implementation of PURM. Experiments demonstrate that PURM significantly delays the onset of reward hacking while improving final reward performance, outperforming baseline methods in both stability and effectiveness.
Abstract:The Entrance Dependent Vehicle Routing Problem (EDVRP) is a variant of the Vehicle Routing Problem (VRP) where the scale of cities influences routing outcomes, necessitating consideration of their entrances. This paper addresses EDVRP in agriculture, focusing on multi-parameter vehicle planning for irregularly shaped fields. To address the limitations of traditional methods, such as heuristic approaches, which often overlook field geometry and entrance constraints, we propose a Joint Probability Distribution Sampling Neural Network (JPDS-NN) to effectively solve the EDVRP. The network uses an encoder-decoder architecture with graph transformers and attention mechanisms to model routing as a Markov Decision Process, and is trained via reinforcement learning for efficient and rapid end-to-end planning. Experimental results indicate that JPDS-NN reduces travel distances by 48.4-65.4%, lowers fuel consumption by 14.0-17.6%, and computes two orders of magnitude faster than baseline methods, while demonstrating 15-25% superior performance in dynamic arrangement scenarios. Ablation studies validate the necessity of cross-attention and pre-training. The framework enables scalable, intelligent routing for large-scale farming under dynamic constraints.
Abstract:Vehicle Routing Problems (VRP) are widely studied issues that play important roles in many production scenarios. We have noticed that in some practical scenarios of VRP, the size of cities and their entrances can significantly influence the optimization process. To address this, we have constructed the Entrance Dependent VRP (EDVRP) to describe such problems. We provide a mathematical formulation for the EDVRP in farms and propose an Ordered Genetic Algorithm (OGA) to solve it. The effectiveness of OGA is demonstrated through our experiments, which involve a multitude of randomly generated cases. The results indicate that OGA offers certain advantages compared to a random strategy baseline and a genetic algorithm without ordering. Furthermore, the novel operators introduced in this paper have been validated through ablation experiments, proving their effectiveness in enhancing the performance of the algorithm.
Abstract:Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in quick, heuristic decisions, System 2 relies on logical reasoning for more accurate judgments and reduced biases. Foundational Large Language Models (LLMs) excel at fast decision-making but lack the depth for complex reasoning, as they have not yet fully embraced the step-by-step analysis characteristic of true System 2 thinking. Recently, reasoning LLMs like OpenAI's o1/o3 and DeepSeek's R1 have demonstrated expert-level performance in fields such as mathematics and coding, closely mimicking the deliberate reasoning of System 2 and showcasing human-like cognitive abilities. This survey begins with a brief overview of the progress in foundational LLMs and the early development of System 2 technologies, exploring how their combination has paved the way for reasoning LLMs. Next, we discuss how to construct reasoning LLMs, analyzing their features, the core methods enabling advanced reasoning, and the evolution of various reasoning LLMs. Additionally, we provide an overview of reasoning benchmarks, offering an in-depth comparison of the performance of representative reasoning LLMs. Finally, we explore promising directions for advancing reasoning LLMs and maintain a real-time \href{https://github.com/zzli2022/Awesome-Slow-Reason-System}{GitHub Repository} to track the latest developments. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this rapidly evolving field.
Abstract:Large language models (LLMs) have shown impressive performance across a wide range of tasks. However, they often exhibit unexpected failures in seemingly straightforward tasks, suggesting a reliance on case-based reasoning rather than rule-based reasoning. While the vast training corpus of LLMs contains numerous textual "rules", current training methods fail to leverage these rules effectively. Crucially, the relationships between these "rules" and their corresponding "instances" are not explicitly modeled. As a result, while LLMs can often recall rules with ease, they fail to apply these rules strictly and consistently in relevant reasoning scenarios. In this paper, we investigate the rule-following capabilities of LLMs and propose Meta Rule-Following Fine-Tuning (Meta-RFFT) to enhance the cross-task transferability of rule-following abilities. We first construct a dataset of 88 tasks requiring following rules, encompassing diverse reasoning domains. We demonstrate through extensive experiments that models trained on large-scale rule-following tasks are better rule followers, outperforming the baselines in both downstream fine-tuning and few-shot prompting scenarios. This highlights the cross-task transferability of models with the aid of Meta-RFFT. Furthermore, we examine the influence of factors such as dataset size, rule formulation, and in-context learning.
Abstract:How to interact with LLMs through \emph{instructions} has been widely studied by researchers. However, previous studies have treated the emergence of instructions and the training of LLMs on task data as separate processes, overlooking the inherent unity between the two. This paper proposes a neural network framework, VaiBot, that integrates VAE and VIB, designed to uniformly model, learn, and infer both deduction and induction tasks under LLMs. Through experiments, we demonstrate that VaiBot performs on par with existing baseline methods in terms of deductive capabilities while significantly surpassing them in inductive capabilities. We also find that VaiBot can scale up using general instruction-following data and exhibits excellent one-shot induction abilities. We finally synergistically integrate the deductive and inductive processes of VaiBot. Through T-SNE dimensionality reduction, we observe that its inductive-deductive process significantly improves the distribution of training parameters, enabling it to outperform baseline methods in inductive reasoning tasks. The code and data for this paper can be found at https://anonymous.4open.science/r/VaiBot-021F.
Abstract:Can scaling transform reasoning? In this work, we explore the untapped potential of scaling Long Chain-of-Thought (Long-CoT) data to 1000k samples, pioneering the development of a slow-thinking model, RedStar. Through extensive experiments with various LLMs and different sizes, we uncover the ingredients for specialization and scale for Long-CoT training. Surprisingly, even smaller models show significant performance gains with limited data, revealing the sample efficiency of Long-CoT and the critical role of sample difficulty in the learning process. Our findings demonstrate that Long-CoT reasoning can be effectively triggered with just a few thousand examples, while larger models achieve unparalleled improvements. We also introduce reinforcement learning (RL)-scale training as a promising direction for advancing slow-thinking systems. RedStar shines across domains: on the MATH-Hard benchmark, RedStar-code-math boosts performance from 66.2\% to 81.6\%, and on the USA Math Olympiad (AIME), it solves 46.7\% of problems using only 21k mixed-code-math datasets. In multimodal tasks like GeoQA and MathVista-GEO, RedStar-Geo achieves competitive results with minimal Long-CoT data, outperforming other slow-thinking systems like QvQ-Preview. Compared to QwQ, RedStar strikes the perfect balance between reasoning and generalizability. Our work highlights that, with careful tuning, scaling Long-CoT can unlock extraordinary reasoning capabilities-even with limited dataset and set a new standard for slow-thinking models across diverse challenges. Our data and models are released at https://huggingface.co/RedStar-Reasoning.
Abstract:We propose SC-MCTS*: a novel Monte Carlo Tree Search (MCTS) reasoning algorithm for Large Language Models (LLMs), significantly improves both reasoning accuracy and speed. Our motivation comes from: 1. Previous MCTS LLM reasoning works often overlooked its biggest drawback--slower speed compared to CoT; 2. Previous research mainly used MCTS as a tool for LLM reasoning on various tasks with limited quantitative analysis or ablation studies of its components from reasoning interpretability perspective. 3. The reward model is the most crucial component in MCTS, however previous work has rarely conducted in-depth study or improvement of MCTS's reward models. Thus, we conducted extensive ablation studies and quantitative analysis on components of MCTS, revealing the impact of each component on the MCTS reasoning performance of LLMs. Building on this, (i) we designed a highly interpretable reward model based on the principle of contrastive decoding and (ii) achieved an average speed improvement of 51.9% per node using speculative decoding. Additionally, (iii) we improved UCT node selection strategy and backpropagation used in previous works, resulting in significant performance improvement. We outperformed o1-mini by an average of 17.4% on the Blocksworld multi-step reasoning dataset using Llama-3.1-70B with SC-MCTS*.
Abstract:The exponential growth in data sizes and storage costs has brought considerable challenges to the data science community, requiring solutions to run learning methods on such data. While machine learning has scaled to achieve predictive accuracy in big data settings, statistical inference and uncertainty quantification tools are still lagging. Priority scientific fields collect vast data to understand phenomena typically studied with statistical methods like regression. In this setting, regression parameter estimation can benefit from efficient computational procedures, but the main challenge lies in computing error process parameters with complex covariance structures. Identifying and estimating these structures is essential for inference and often used for uncertainty quantification in machine learning with Gaussian Processes. However, estimating these structures becomes burdensome as data scales, requiring approximations that compromise the reliability of outputs. These approximations are even more unreliable when complexities like long-range dependencies or missing data are present. This work defines and proves the statistical properties of the Generalized Method of Wavelet Moments with Exogenous variables (GMWMX), a highly scalable, stable, and statistically valid method for estimating and delivering inference for linear models using stochastic processes in the presence of data complexities like latent dependence structures and missing data. Applied examples from Earth Sciences and extensive simulations highlight the advantages of the GMWMX.
Abstract:Task-aware navigation continues to be a challenging area of research, especially in scenarios involving open vocabulary. Previous studies primarily focus on finding suitable locations for task completion, often overlooking the importance of the robot's pose. However, the robot's orientation is crucial for successfully completing tasks because of how objects are arranged (e.g., to open a refrigerator door). Humans intuitively navigate to objects with the right orientation using semantics and common sense. For instance, when opening a refrigerator, we naturally stand in front of it rather than to the side. Recent advances suggest that Vision-Language Models (VLMs) can provide robots with similar common sense. Therefore, we develop a VLM-driven method called Navigation-to-Gaze (Navi2Gaze) for efficient navigation and object gazing based on task descriptions. This method uses the VLM to score and select the best pose from numerous candidates automatically. In evaluations on multiple photorealistic simulation benchmarks, Navi2Gaze significantly outperforms existing approaches and precisely determines the optimal orientation relative to target objects.