While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven substantial performance improvements, but existing compilers struggle with neural workloads due to the exponentially large and highly interdependent space of possible transformations. Although existing stochastic search techniques can be effective, they are often sample-inefficient and fail to leverage the structural context underlying compilation decisions. We set out to investigate the research question of whether reasoning with large language models (LLMs), without any retraining, can leverage the context-aware decision space of compiler optimizations to significantly improve sample efficiency. To that end, we introduce a novel compilation framework (dubbed REASONING COMPILER) that formulates optimization as a sequential, context-aware decision process guided by a large language model and structured Monte Carlo tree search (MCTS). The LLM acts as a proposal mechanism, suggesting hardware-informed transformations that reflect the current program state and accumulated performance feedback. MCTS incorporates the LLM-generated proposals to balance exploration and exploitation, facilitating a structured, context-sensitive traversal of the expansive compiler optimization space. By achieving substantial speedups with markedly fewer samples than leading neural compilers, our approach demonstrates the potential of LLM-guided reasoning to transform the landscape of compiler optimization.

Tabular reasoning requires complex, multi-step information extraction and logical inference, such as aggregation, comparison, or calculation over tabular data. While recent advances have leveraged large language models (LLMs) for reasoning over structured text tables, such high-quality textual representations are often unavailable in real-world settings, where tables typically appear as images. In this paper, we tackle the task of tabular reasoning directly from table images. Our core strategy is to leverage privileged structured information---specifically, the ground-truth structured table data available during training but inaccessible at test time---to enhance multimodal large language models (MLLMs). The key challenges lie in: accurately aligning visual representations with the structured information, particularly mapping the visual evidence to logical steps; and effectively transferring the reasoning skills learned during training to the MLLM for visual inference. To address these, we introduce {\sc Turbo} (TabUlar Reasoning with Bridged infOrmation), a new framework for multimodal tabular reasoning using privileged information.

The ability to actively acquire information is essential for open-world planning under partial observability and incomplete knowledge. However, most existing embodied AI systems either assume a known object category or rely on passive perception strategies that exhaustively gather object and relational information from the environment. Such a strategy becomes insufficient in visually complex open-world settings. For instance, a typical household may contain thousands of novel and uniquely configured objects, most of which are irrelevant to the agent's current task. Consequently, open-world agents must be capable of actively identifying and prioritizing task-relevant objects to enable efficient and goal-directed knowledge acquisition. In this work, we introduce ActiveVOO, a novel zero-shot framework for open-world embodied planning that emphasizes object-centric active knowledge acquisition. ActiveVOO employs lifted regression to generate compact, first-order subgoal descriptions that identify task-relevant objects, and provides a principled mechanism to quantify the utility of sensing actions based on commonsense priors derived from LLMs and VLMs. We evaluate ActiveVOO on the visual ALFWorld benchmark, where it achieves substantial improvements over existing LLMand VLM-based planning approaches, notably outperforming VLMs fine-tuned on ALFWorld data. This work establishes a principled foundation for developing embodied agents capable of actively and efficiently acquiring knowledge to plan and act in open-world environments.

Uncertainty quantification for Large Language Models (LLMs) encompasses a diverse range of approaches, with two major families being particularly prominent: (i) information-based, which estimate model confidence from token-level probabilities, and (ii) consistency-based, which assess the semantic agreement among multiple outputs generated using repeated sampling. While several recent methods have sought to combine these two paradigms to improve uncertainty quantification performance, they often fail to consistently outperform simpler baselines. In this work, we revisit the foundations of uncertainty estimation through the lens of Minimum Bayes Risk decoding, establishing a direct link between uncertainty and the optimal decision-making process of LLMs. Building on these findings, we propose CoCoA, a unified framework that integrates model confidence with output consistency, yielding a family of efficient and robust uncertainty quantification methods. We evaluate CoCoA across diverse tasks, including question answering, abstractive text summarization, and machine translation, and demonstrate sizable improvements over state-of-the-art uncertainty quantification approaches.

Optimization modeling is fundamental to decision-making in fields such as supply chain management, logistics, and financial engineering, but its complexity presents a major barrier to adoption. Automating model creation from natural language is key to improving efficiency and access. However, while Large Language Models (LLMs) are a promising tool for this, they often produce flawed or infeasible results due to errors and hallucinations. To address this issue, we propose Solver-Informed Reinforcement Learning (SIRL), a framework that uses Reinforcement Learning with Verifiable Reward to improve LLMs' ability to generate accurate and executable optimization models. Specifically, SIRL automatically assesses the executable code and the instance-level mathematical model represented by the associated .lp

Current 3D gaze estimation methods struggle to generalize across diverse data domains, primarily due to $\textbf{i)}$ $\textit{the scarcity of annotated datasets}$, and $\textbf{ii)}$ $\textit{the insufficient diversity of labeled data}$. In this work, we present OmniGaze, a semi-supervised framework for 3D gaze estimation, which utilizes large-scale unlabeled data collected from diverse and unconstrained real-world environments to mitigate domain bias and generalize gaze estimation in the wild. First, we build a diverse collection of unlabeled facial images, varying in facial appearances, background environments, illumination conditions, head poses, and eye occlusions. In order to leverage unlabeled data spanning a broader distribution, OmniGaze adopts a standard pseudo-labeling strategy and devises a reward model to assess the reliability of pseudo labels. Beyond pseudo labels as 3D direction vectors, the reward model also incorporates visual embeddings extracted by an off-the-shelf visual encoder and semantic cues from gaze perspective generated by prompting a Multimodal Large Language Model to compute confidence scores. Then, these scores are utilized to select high-quality pseudo labels and weight them for loss computation. Extensive experiments demonstrate that OmniGaze achieves state-of-the-art performance on five datasets under both in-domain and cross-domain settings. Furthermore, we also evaluate the efficacy of OmniGaze as a scalable data engine for gaze estimation, which exhibits robust zero-shot generalization on four unseen datasets.

Integrating the understanding and reasoning capabilities of Large Language Models (LLM) with the self-learning capabilities of Reinforcement Learning (RL) enables more reliable driving performance under complex driving conditions. There has been a lot of work exploring LLM-Dominated RL methods in the field of autonomous driving motion planning. These methods, which utilize LLM to directly generate policies or provide decisive instructions during policy learning of RL agent, are centrally characterized by an over-reliance on LLM outputs. However, LLM outputs are susceptible to hallucinations. Evaluations show that state-of-the-art LLM indicates a non-hallucination rate of only approximately 57.95\% when assessed on essential driving-related tasks. Thus, in these methods, hallucinations from the LLM can directly jeopardize the performance of driving policies.

The fine-tuning of pre-trained large language models (LLMs) using reinforcement learning (RL) is generally formulated as direct policy optimization. This approach was naturally favored as it efficiently improves a pretrained LLM with simple gradient updates. Another RL paradigm, Q-learning methods, has received far less attention in the LLM community while demonstrating major success in various non-LLM RL tasks. In particular, Q-learning effectiveness stems from its sample efficiency and ability to learn offline, which is particularly valuable given the high computational cost of sampling with LLM. However, naively applying a Q-learning-style update to the model's logits is ineffective due to the specificity of LLMs.

Training large language models (LLMs) from scratch can yield models with unique functionalities and strengths, but it is costly and often leads to redundant capabilities. A more cost-effective alternative is to fuse existing pre-trained LLMs with different architectures into a more powerful model. However, a key challenge in existing model fusion is their dependence on manually predefined vocabulary alignment, which may not generalize well across diverse contexts, leading to performance degradation in several evaluation. To solve this, we draw inspiration from distribution learning and propose the probabilistic token alignment method as a general and soft mapping for alignment, named as PTA-LLM. Our approach innovatively reformulates token alignment into a classic mathematical problem: optimal transport, seamlessly leveraging distribution-aware learning to facilitate more coherent model fusion. Apart from its inherent generality, PTA-LLM exhibits interpretability from a distributional perspective, offering insights into the essence of the token alignment. Empirical results demonstrate that probabilistic token alignment enhances the target model's performance across multiple capabilities.

Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool use scenarios. Recent advancements in reinforcement learning (RL), particularly with R1-like models, have demonstrated promising reasoning and generalization abilities. Yet, reward design for tool use presents unique challenges: multiple tools may be invoked with diverse parameters, and coarse-grained reward signals, such as answer matching, fail to offer the finegrained feedback required for effective learning. In this work, we present the first comprehensive study on reward design for tool selection and application tasks within the RL paradigm. We systematically explore a wide range of reward strategies, analyzing their types, scales, granularity, and temporal dynamics. Building on these insights, we propose a principled reward design tailored for tool use tasks and apply it to train LLMs using RL methods. Empirical evaluations across diverse benchmarks demonstrate that our approach yields robust, scalable, and stable training, achieving a 17\% improvement over base models and a 15\% gain over SFT models.