Omni-DPO: A Dual-Perspective Paradigm for Dynamic Preference Learning of LLMs

Direct Preference Optimization (DPO) has become a cornerstone of reinforcement learning from human feedback (RLHF) due to its simplicity and efficiency. However, existing DPO-based approaches typically treat all preference pairs uniformly, ignoring critical variations in their inherent quality and learning utility, leading to suboptimal data utilization and performance. To address this challenge, we propose Omni-DPO, a dual-perspective optimization framework that jointly accounts for (1) the inherent quality of each preference pair and (2) the model's evolving performance on those pairs. By adaptively weighting samples according to both data quality and the model's learning dynamics during training, Omni-DPO enables more effective training data utilization and achieves better performance. Experimental results on various models and benchmarks demonstrate the superiority and generalization capabilities of Omni-DPO. On textual understanding tasks, Gemma-2-9b-it finetuned with Omni-DPO beats the leading LLM, Claude 3 Opus, by a significant margin of 6.7 points on the Arena-Hard benchmark. On mathematical reasoning tasks, Omni-DPO consistently outperforms the baseline methods across all benchmarks, providing strong empirical evidence for the effectiveness and robustness of our approach. Code and models will be available at https://github.com/pspdada/Omni-DPO.

Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving

Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents autonomously learn to leverage external tools like code execution remains crucial. We investigate RL from outcome-based rewards for Tool-Integrated Reasoning, ZeroTIR, training base LLMs to spontaneously generate and execute Python code for mathematical problems without supervised tool-use examples. Our central contribution is we demonstrate that as RL training progresses, key metrics scale predictably. Specifically, we observe strong positive correlations where increased training steps lead to increases in the spontaneous code execution frequency, the average response length, and, critically, the final task accuracy. This suggests a quantifiable relationship between computational effort invested in training and the emergence of effective, tool-augmented reasoning strategies. We implement a robust framework featuring a decoupled code execution environment and validate our findings across standard RL algorithms and frameworks. Experiments show ZeroTIR significantly surpasses non-tool ZeroRL baselines on challenging math benchmarks. Our findings provide a foundational understanding of how autonomous tool use is acquired and scales within Agent RL, offering a reproducible benchmark for future studies. Code is released at \href{https://github.com/yyht/openrlhf_async_pipline}{https://github.com/yyht/openrlhf\_async\_pipline}.

GeoNav: Empowering MLLMs with Explicit Geospatial Reasoning Abilities for Language-Goal Aerial Navigation

Language-goal aerial navigation is a critical challenge in embodied AI, requiring UAVs to localize targets in complex environments such as urban blocks based on textual specification. Existing methods, often adapted from indoor navigation, struggle to scale due to limited field of view, semantic ambiguity among objects, and lack of structured spatial reasoning. In this work, we propose GeoNav, a geospatially aware multimodal agent to enable long-range navigation. GeoNav operates in three phases-landmark navigation, target search, and precise localization-mimicking human coarse-to-fine spatial strategies. To support such reasoning, it dynamically builds two different types of spatial memory. The first is a global but schematic cognitive map, which fuses prior textual geographic knowledge and embodied visual cues into a top-down, annotated form for fast navigation to the landmark region. The second is a local but delicate scene graph representing hierarchical spatial relationships between blocks, landmarks, and objects, which is used for definite target localization. On top of this structured representation, GeoNav employs a spatially aware, multimodal chain-of-thought prompting mechanism to enable multimodal large language models with efficient and interpretable decision-making across stages. On the CityNav urban navigation benchmark, GeoNav surpasses the current state-of-the-art by up to 12.53% in success rate and significantly improves navigation efficiency, even in hard-level tasks. Ablation studies highlight the importance of each module, showcasing how geospatial representations and coarse-to-fine reasoning enhance UAV navigation.

Probabilistic Uncertain Reward Model: A Natural Generalization of Bradley-Terry Reward Model

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.

JPDS-NN: Reinforcement Learning-Based Dynamic Task Allocation for Agricultural Vehicle Routing Optimization

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.

Ordered Genetic Algorithm for Entrance Dependent Vehicle Routing Problem in Farms

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.

From System 1 to System 2: A Survey of Reasoning Large Language Models

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.

Training Large Language Models to be Better Rule Followers

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.

VaiBot: Shuttle Between the Instructions and Parameters

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.

RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?

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.