Chain-of-Thought (CoT) and its variants have markedly advanced the reasoning abilities of Large Language Models (LLMs), yet their monolithic and auto-regressive architecture inherently conflates high-level strategic planning with low-level step-by-step execution, leading to computational inefficiency, limited exploration of reasoning paths, and reduced interpretability. To overcome these issues, we propose the Explore-Execute Chain ($E^2C$), a structured reasoning framework that decouples reasoning into two distinct phases: an exploratory phase that stochastically generates succinct high-level plans, followed by an execution phase that deterministically carries out the chosen plan. Our approach incorporates a two-stage training methodology, which combines Supervised Fine-Tuning (SFT) - augmented by a novel data generation algorithm enforcing strict plan adherence - with a subsequent Reinforcement Learning (RL) stage that capitalizes on the informativeness of exploration and reinforces the determinism of execution. This decomposition enables an efficient test-time scaling strategy: on AIME'2024, $E^2C$ Test Time Scaling reaches 58.1% accuracy using <10% of the decoding tokens required by comparable methods (e.g., Forest-of-Thought), sharply cutting self-consistency overhead. For cross-domain adaptation, our Exploration-Focused SFT (EF-SFT) fine-tunes with only 3.5% of the tokens used by standard SFT yet yields up to 14.5% higher accuracy than standard SFT on medical benchmarks, delivering state-of-the-art performance, strong generalization, and greater interpretability by separating planning from execution. The code and pre-trained models for the project are available at: https://github.com/yks23/Explore-Execute-Chain.git

Large language models (LLMs) have shown promising performance on tasks that require reasoning, such as text-to-SQL, code generation, and debugging. However, regulatory frameworks with strict privacy requirements constrain their integration into sensitive systems. State-of-the-art LLMs are also proprietary, costly, and resource-intensive, making local deployment impractical. Consequently, utilizing such LLMs often requires sharing data with third-party providers, raising privacy concerns and risking noncompliance with regulations. Although fine-tuned small language models (SLMs) can outperform LLMs on certain tasks and be deployed locally to mitigate privacy concerns, they underperform on more complex tasks such as text-to-SQL translation. In this work, we introduce MaskSQL, a text-to-SQL framework that utilizes abstraction as a privacy protection mechanism to mask sensitive information in LLM prompts. Unlike redaction, which removes content entirely, or generalization, which broadens tokens, abstraction retains essential information while discarding unnecessary details, striking an effective privacy-utility balance for the text-to-SQL task. Moreover, by providing mechanisms to control the privacy-utility tradeoff, MaskSQL facilitates adoption across a broader range of use cases. Our experimental results show that MaskSQL outperforms leading SLM-based text-to-SQL models and achieves performance approaching state-of-the-art LLM-based models, while preserving privacy.

Tool-Integrated Reasoning (TIR) enables large language models (LLMs) to improve their internal reasoning ability by integrating external tools. However, models employing TIR often display suboptimal behaviors, such as insufficient or excessive tool usage and overthinking after tool calls. The challenge of incentivizing LLMs to perform TIR efficiently and accurately, while stabilizing the reasoning process, remains an open question. In this paper, we start by exploring the impact of tool calls on model reasoning from the perspective of information entropy. Our findings indicate that tool call results lead to a distinct change in the information entropy of subsequent reasoning, with the overall entropy of the reasoning chain varying based on the number of tool calls. Building on these insights, we propose Tool-Light, a framework designed to encourage LLMs to perform TIR efficiently and accurately. Our framework includes dataset construction and multi-stage fine-tuning. For dataset construction, we employ continuous self-evolved sampling using the fine-tuned model, integrating both vanilla sampling and entropy-guided sampling. Besides, we establish strict criteria for selecting positive-negative pairs during sampling. The training process involves a two-stage approach, comprising Supervised Fine-Tuning (SFT) and Self-Evolved Direct Preference Optimization (DPO). Experimental results on 10 datasets demonstrate the effectiveness of Tool-Light, significantly improving the model's efficiency in executing TIR tasks.

This study offers a novel approach for benchmarking complex cognitive behavior in artificial systems. Almost universally, Large Language Models (LLMs) perform best on tasks which may be included in their training data and can be accomplished solely using natural language, limiting our understanding of their emergent sophisticated cognitive capacities. In this work, we created dozens of novel items of a classic mental imagery task from cognitive psychology. A task which, traditionally, cognitive psychologists have argued is solvable exclusively via visual mental imagery (i.e., language alone would be insufficient). LLMs are perfect for testing this hypothesis. First, we tested several state-of-the-art LLMs by giving text-only models written instructions and asking them to report the resulting object after performing the transformations in the aforementioned task. Then, we created a baseline by testing 100 human subjects in exactly the same task. We found that the best LLMs performed significantly above average human performance. Finally, we tested reasoning models set to different levels of reasoning and found the strongest performance when models allocate greater amounts of reasoning tokens. These results provide evidence that the best LLMs may have the capability to complete imagery-dependent tasks despite the non-pictorial nature of their architectures. Our study not only demonstrates an emergent cognitive capacity in LLMs while performing a novel task, but it also provides the field with a new task that leaves lots of room for improvement in otherwise already highly capable models. Finally, our findings reignite the debate over the formats of representation of visual imagery in humans, suggesting that propositional reasoning (or at least non-imagistic reasoning) may be sufficient to complete tasks that were long-thought to be imagery-dependent.

Perceptual losses have emerged as powerful tools for training networks to enhance Low-Dose Computed Tomography (LDCT) images, offering an alternative to traditional pixel-wise losses such as Mean Squared Error, which often lead to over-smoothed reconstructions and loss of clinically relevant details in LDCT images. The perceptual losses operate in a latent feature space defined by a pretrained encoder and aim to preserve semantic content by comparing high-level features rather than raw pixel values. However, the design of perceptual losses involves critical yet underexplored decisions, including the feature representation level, the dataset used to pretrain the encoder, and the relative importance assigned to the perceptual component during optimization. In this work, we introduce the concept of perceptual influence (a metric that quantifies the relative contribution of the perceptual loss term to the total loss) and propose a principled framework to assess the impact of the loss design choices on the model training performance. Through systematic experimentation, we show that the widely used configurations in the literature to set up a perceptual loss underperform compared to better-designed alternatives. Our findings show that better perceptual loss designs lead to significant improvements in noise reduction and structural fidelity of reconstructed CT images, without requiring any changes to the network architecture. We also provide objective guidelines, supported by statistical analysis, to inform the effective use of perceptual losses in LDCT denoising. Our source code is available at https://github.com/vngabriel/perceptual-influence.

Visual personalization is essential in user-facing AI systems such as smart homes and healthcare, where aligning model behavior with user-centric concepts is critical. However, recent large Vision-Language Models (VLMs), despite their broad applicability, remain underexplored in their ability to adapt to individual users. In this paper, we introduce MMPB, the first extensive benchmark for evaluating VLMs on personalization. MMPB comprises 10k image-query pairs and includes 111 personalizable concepts across four categories: humans, animals, objects, and characters, with the human category enriched with preference-grounded queries. We structure personalization into three main task types, each highlighting a different key property of VLMs. Using 23 widely used VLMs including both open- and closed-source models, we evaluate personalization performance via a three-stage protocol: concept injection, multi-turn dialogue, and personalized querying. Our findings indicate that most VLMs (including some closed-source models) struggle with personalization, particularly in maintaining consistency over dialogue, handling user preferences, and adapting to visual cues. Our analysis reveals that the challenges in VLM personalization (such as refusal behaviors and long-context forgetting) highlight substantial room for improvement. By identifying these limitations and offering a scalable benchmark, MMPB offers valuable insights and a solid foundation for future research toward truly personalized multi-modal AI. Project Page: aidaslab.github.io/MMPB

Large language models (LLMs) are increasingly positioned as solutions for education, yet evaluations often reduce their impact to narrow performance metrics. This paper reframes the question by asking "what kind of impact should LLMs have in education?" Drawing on Biesta's tripartite account of good education: qualification, socialisation, and subjectification, we present a meta-analysis of 133 experimental and quasi-experimental studies (k = 188). Overall, the impact of LLMs on student learning is positive but uneven. Strong effects emerge in qualification, particularly when LLMs function as tutors in sustained interventions. Socialisation outcomes appear more variable, concentrated in sustained, reflective interventions. Subjectification, linked to autonomy and learner development, remains fragile, with improvements confined to small-scale, long-term studies. This purpose-level view highlights design as the decisive factor: without scaffolds for participation and agency, LLMs privilege what is easiest to measure while neglecting broader aims of education. For HCI and education, the issue is not just whether LLMs work, but what futures they enable or foreclose.

Chain-of-Thought (CoT) prompting improves reasoning in large language models (LLMs), but its reliance on unstructured text limits interpretability and executability in embodied tasks. Prior work has explored structured CoTs using scene or logic graphs, yet these remain fundamentally limited: they model only low-order relations, lack constructs like inheritance or behavioral abstraction, and provide no standardized semantics for sequential or conditional planning. We propose UML-CoT, a structured reasoning and planning framework that leverages Unified Modeling Language (UML) to generate symbolic CoTs and executable action plans. UML class diagrams capture compositional object semantics, while activity diagrams model procedural control flow. Our three-stage training pipeline combines supervised fine-tuning with Group Relative Policy Optimization (GRPO), including reward learning from answer-only data. We evaluate UML-CoT on MRoom-30k, a new benchmark of cluttered room-cleaning scenarios. UML-CoT outperforms unstructured CoTs in interpretability, planning coherence, and execution success, highlighting UML as a more expressive and actionable structured reasoning formalism.

As language model (LM) agents become more capable and gain broader access to real-world tools, there is a growing need for scalable evaluation frameworks of agentic capability. However, conventional benchmark-centric evaluations are costly to design and require human designers to come up with valid tasks that translate into insights about general model capabilities. In this work, we propose information-theoretic evaluation based on empowerment, the mutual information between an agent's actions and future states, as an open-ended method for evaluating LM agents. We introduce EELMA (Estimating Empowerment of Language Model Agents), an algorithm for approximating effective empowerment from multi-turn text interactions. We validate EELMA on both language games and scaled-up realistic web-browsing scenarios. We find that empowerment strongly correlates with average task performance, characterize the impact of environmental complexity and agentic factors such as chain-of-thought, model scale, and memory length on estimated empowerment, and that high empowerment states and actions are often pivotal moments for general capabilities. Together, these results demonstrate empowerment as an appealing general-purpose metric for evaluating and monitoring LM agents in complex, open-ended settings.

Large Language Model (LLM) agents have demonstrated remarkable capabilities in organizing and executing complex tasks, and many such agents are now widely used in various application scenarios. However, developing these agents requires carefully designed workflows, carefully crafted prompts, and iterative tuning, which requires LLM techniques and domain-specific expertise. These handcrafted limitations hinder the scalability and cost-effectiveness of LLM agents across a wide range of industries. To address these challenges, we propose InfiA-gent, a Pyramid-like DAG-based Multi-Agent Framework that can be applied to infinite scenarios, which introduces several key innovations: a generalized "agent-as-a-tool" mechanism that automatically decomposes complex agents into hierarchical multi-agent systems; a dual-audit mechanism that ensures the quality and stability of task completion; an agent routing function that enables efficient task-agent matching; and an agent self-evolution mechanism that autonomously restructures the agent DAG based on new tasks, poor performance, or optimization opportunities. Furthermore, InfiAgent's atomic task design supports agent parallelism, significantly improving execution efficiency. Evaluations on multiple benchmarks demonstrate that InfiAgent achieves 9.9% higher performance compared to ADAS (similar auto-generated agent framework), while a case study of the AI research assistant InfiHelper shows that it generates scientific papers that have received recognition from human reviewers at top-tier IEEE conferences. The rapid development of large-scale language models (LLMs) has ushered in a new era of intelligent automation (Naveed et al., 2025; Tran et al., 2025), with agent-based systems demonstrating remarkable capabilities in organizing and executing complex tasks across domains. From scientific research and software development to creative content generation and business process automation, LLM agents are transforming how we solve problems at scale. However, the development and deployment of these agents face significant challenges, limiting their widespread adoption and effectiveness. Current approaches to building LLM agents rely heavily on carefully designed workflows, carefully crafted prompts, and extensive iterative tuning--processes that require deep LLM expertise and domain-specific knowledge (V eeramachaneni, 2025; Guo et al., 2024; Annam et al., 2025; Schick et al., 2023). This reliance on handcrafted solutions creates a fundamental scalability barrier: each new application requires significant manual intervention, making it difficult to rapidly deploy agents across diverse industries and use cases.