Autoformalization, the process of transforming informal mathematical propositions into verifiable formal representations, is a foundational task in automated theorem proving, offering a new perspective on the use of mathematics in both theoretical and applied domains. Driven by the rapid progress in artificial intelligence, particularly large language models (LLMs), this field has witnessed substantial growth, bringing both new opportunities and unique challenges. In this survey, we provide a comprehensive overview of recent advances in autoformalization from both mathematical and LLM-centric perspectives. We examine how autoformalization is applied across various mathematical domains and levels of difficulty, and analyze the end-to-end workflow from data preprocessing to model design and evaluation. We further explore the emerging role of autoformalization in enhancing the verifiability of LLM-generated outputs, highlighting its potential to improve both the trustworthiness and reasoning capabilities of LLMs. Finally, we summarize key open-source models and datasets supporting current research, and discuss open challenges and promising future directions for the field.

Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind autoregressive models due to the lack of Key-Value (KV) Cache and quality degradation when decoding multiple tokens simultaneously. To bridge this gap, we introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop. Additionally, we identify the root cause of generation quality degradation in parallel decoding as the disruption of token dependencies under the conditional independence assumption. To address this, we propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality. Experimental results on LLaDA and Dream models across multiple LLM benchmarks demonstrate up to \textbf{27.6$\times$ throughput} improvement with minimal accuracy loss, closing the performance gap with autoregressive models and paving the way for practical deployment of Diffusion LLMs.

University College London Summary This study presents an innovative approach to urban mobility simulation by integrating a Large Language Model (LLM) with Agent-Based Modeling (ABM). Unlike traditional rule-based ABM, the proposed framework leverages LLM to enhance agent diversity and realism by generating synthetic population profiles, allocating routine and occasional locations, and simulating personalized routes. Key insights, such as route heat maps and mode-specific indicators, provide urban planners with actionable information for policy-making. Future work focuses on establishing robust validation frameworks to ensure accuracy and reliability in urban planning applications. KEYWORDS: Mobility simulation, Agent-Based Modeling (ABM), Large Language Model (LLM), Synthetic profiles, Urban planning 1. Introduction Mobility reflects the unique geographic, economic, and cultural contexts of cities while being shaped by and confined to the urban infrastructure that supports it.

Recent advances in AI are transforming AI's ubiquitous presence in our world from that of standalone AI-applications into deeply integrated AI-agents. These changes have been driven by agents' increasing capability to autonomously make decisions and initiate actions, using existing applications; whether those applications are AI-based or not. This evolution enables unprecedented levels of AI integration, with agents now able to take actions on behalf of systems and users -- including, in some cases, the powerful ability for the AI to write and execute scripts as it deems necessary. With AI systems now able to autonomously execute code, interact with external systems, and operate without human oversight, traditional security approaches fall short. This paper introduces an asset-centric methodology for threat modeling AI systems that addresses the unique security challenges posed by integrated AI agents. Unlike existing top-down frameworks that analyze individual attacks within specific product contexts, our bottom-up approach enables defenders to systematically identify how vulnerabilities -- both conventional and AI-specific -- impact critical AI assets across distributed infrastructures used to develop and deploy these agents. This methodology allows security teams to: (1) perform comprehensive analysis that communicates effectively across technical domains, (2) quantify security assumptions about third-party AI components without requiring visibility into their implementation, and (3) holistically identify AI-based vulnerabilities relevant to their specific product context. This approach is particularly relevant for securing agentic systems with complex autonomous capabilities. By focusing on assets rather than attacks, our approach scales with the rapidly evolving threat landscape while accommodating increasingly complex and distributed AI development pipelines.

Multi-agent frameworks with Large Language Models (LLMs) have become promising tools for generating general-purpose programming languages using test-driven development, allowing developers to create more accurate and robust code. However, their potential has not been fully unleashed for domain-specific programming languages, where specific domain exhibits unique optimization opportunities for customized improvement. In this paper, we take the first step in exploring multi-agent code generation for quantum programs. By identifying the unique optimizations in quantum designs such as quantum error correction, we introduce a novel multi-agent framework tailored to generating accurate, fault-tolerant quantum code. Each agent in the framework focuses on distinct optimizations, iteratively refining the code using a semantic analyzer with multi-pass inference, alongside an error correction code decoder. We also examine the effectiveness of inference-time techniques, like Chain-of-Thought (CoT) and Retrieval-Augmented Generation (RAG) in the context of quantum programming, uncovering observations that are different from general-purpose code generation. To evaluate our approach, we develop a test suite to measure the impact each optimization has on the accuracy of the generated code. Our findings indicate that techniques such as structured CoT significantly improve the generation of quantum algorithms by up to 50%. In contrast, we have also found that certain techniques such as RAG show limited improvement, yielding an accuracy increase of only 4%. Moreover, we showcase examples of AI-assisted quantum error prediction and correction, demonstrating the effectiveness of our multi-agent framework in reducing the quantum errors of generated quantum programs.

Relational Triple Extraction (RTE) is a fundamental task in Natural Language Processing (NLP). However, prior research has primarily focused on optimizing model performance, with limited efforts to understand the internal mechanisms driving these models. Many existing methods rely on complex preprocessing to induce specific interactions, often resulting in opaque systems that may not fully align with their theoretical foundations. To address these limitations, we propose SMARTe: a Slot-based Method for Accountable Relational Triple extraction. SMARTe introduces intrinsic interpretability through a slot attention mechanism and frames the task as a set prediction problem. Slot attention consolidates relevant information into distinct slots, ensuring all predictions can be explicitly traced to learned slot representations and the tokens contributing to each predicted relational triple. While emphasizing interpretability, SMARTe achieves performance comparable to state-of-the-art models. Evaluations on the NYT and WebNLG datasets demonstrate that adding interpretability does not compromise performance. Furthermore, we conducted qualitative assessments to showcase the explanations provided by SMARTe, using attention heatmaps that map to their respective tokens. We conclude with a discussion of our findings and propose directions for future research. Our code is available at https://github.com/Chen-XueWen/SMARTe.

Reinforcement learning with verifiable rewards (RL VR) is a promising approach for improving the complex reasoning abilities of large language models (LLMs). However, current RL VR methods face two significant challenges: the near-miss reward problem, where a small mistake can invalidate an otherwise correct reasoning process, greatly hindering training efficiency; and exploration stagnation, where models tend to focus on solutions within their "comfort zone," lacking the motivation to explore potentially more effective alternatives. To address these challenges, we propose StepHint, a novel RL VR algorithm that utilizes multi-level stepwise hints to help models explore the solution space more effectively. StepHint generates valid reasoning chains from stronger models and partitions these chains into reasoning steps using our proposed adaptive partitioning method. The initial few steps are used as hints, and simultaneously, multiple-level hints (each comprising a different number of steps) are provided to the model. This approach directs the model's exploration toward a promising solution subspace while preserving its flexibility for independent exploration. Additionally, the external reasoning pathways help the model develop better reasoning abilities, enabling it to move beyond its "comfort zone" and mitigate exploration stagnation. StepHint outperforms competitive RL VR enhancement methods across six mathematical benchmarks, while also demonstrating superior generalization and excelling over baselines on out-of-domain benchmarks. Eliciting the reasoning capabilities of large language models (LLMs) through Reinforcement Learning with V er-ifiable Rewards (RL VR) has emerged as a powerful paradigm (Jaech et al., 2024; Guo et al., 2025a). In RL VR frameworks, a policy model explores the solution space by generating reasoning chains.

With the widespread adoption of large language models (LLMs) in practical applications, selecting an appropriate model requires balancing not only performance but also operational cost. The emergence of reasoning-capable models has further widened the cost gap between "thinking" (high reasoning) and "non-thinking" (fast, low-cost) modes. In this work, we reveal that approximately 58% of medical questions can be accurately answered by the non-thinking mode alone, without requiring the high-cost reasoning process. This highlights a clear dichotomy in problem complexity and suggests that dynamically routing queries to the appropriate mode based on complexity could optimize accuracy, cost-efficiency, and overall user experience. Based on this, we further propose SynapseRoute, a machine learning-based dynamic routing framework that intelligently assigns input queries to either thinking or non-thinking modes. Experimental results on several medical datasets demonstrate that SynapseRoute not only improves overall accuracy (0.8390 vs. 0.8272) compared to the thinking mode alone but also reduces inference time by 36.8% and token consumption by 39.66%. Importantly, qualitative analysis indicates that over-reasoning on simpler queries can lead to unnecessary delays and even decreased accuracy, a pitfall avoided by our adaptive routing. Finally, this work further introduces the Accuracy-Inference-Token (AIT) index to comprehensively evaluate the trade-offs among accuracy, latency, and token cost.

Recent advances in machine learning have dramatically improved our ability to model language, vision, and other high-dimensional data, yet they continue to struggle with one of the most fundamental aspects of biological systems: movement. Across neuroscience, medicine, robotics, and ethology, movement is essential for interpreting behavior, predicting intent, and enabling interaction. Despite its core significance in our intelligence, movement is often treated as an afterthought rather than as a rich and structured modality in its own right. This reflects a deeper fragmentation in how movement data is collected and modeled, often constrained by task-specific goals and domain-specific assumptions. But movement is not domain-bound. It reflects shared physical constraints, conserved morphological structures, and purposeful dynamics that cut across species and settings. We argue that movement should be treated as a primary modeling target for AI. It is inherently structured and grounded in embodiment and physics. This structure, often allowing for compact, lower-dimensional representations (e.g., pose), makes it more interpretable and computationally tractable to model than raw, high-dimensional sensory inputs. Developing models that can learn from and generalize across diverse movement data will not only advance core capabilities in generative modeling and control, but also create a shared foundation for understanding behavior across biological and artificial systems. Movement is not just an outcome, it is a window into how intelligent systems engage with the world.

Reasoning remains a challenging task for large language models (LLMs), especially within the logically constrained environment of automated theorem proving (A TP), due to sparse rewards and the vast scale of proofs. These challenges are amplified in benchmarks like PutnamBench, which contains university-level problems requiring complex, multi-step reasoning. To address this, we introduce self-generated goal-conditioned MDPs (sG-MDPs), a new framework in which agents generate and pursue their subgoals based on the evolving proof state. Given this more structured generation of goals, the resulting problem becomes more amenable to search. We then apply Monte Carlo Tree Search (MCTS)-like algorithms to solve the sG-MDP, instantiating our approach in Bourbaki (7B), a modular system that can ensemble multiple 7B LLMs for subgoal generation and tactic synthesis. On PutnamBench, Bourbaki (7B) solves 26 problems, achieving new state-of-the-art results with models at this scale. Reasoning is one of the most important skills in human intelligence, and building machines that can reason is a key goal in artificial intelligence.