Large Language Models (LLMs) and Vision Language Models (VLMs) have been widely used for embodied symbolic planning. Y et, how to effectively use these models for closed-loop symbolic planning remains largely unexplored. Because they operate as black boxes, LLMs and VLMs can produce unpredictable or costly errors, making their use in high-level robotic planning especially challenging. In this work, we investigate how to use VLMs as closed-loop symbolic planners for robotic applications from a control-theoretic perspective. Concretely, we study how the control horizon and warm-starting impact the performance of VLM symbolic planners. We design and conduct controlled experiments to gain insights that are broadly applicable to utilizing VLMs as closed-loop symbolic planners, and we discuss recommendations that can help improve the performance of VLM symbolic planners. The project website can be found here.

Large language models (LLMs) have achieved impressive results on complex reasoning tasks, but their high inference cost remains a major barrier to real-world deployment. A promising solution is to use cascaded inference, where small, cheap models handle easy queries, and only the hardest examples are escalated to more powerful models. However, existing cascade methods typically rely on supervised training with labeled data, offer no theoretical generalization guarantees, and provide limited control over test-time computational cost. We introduce C3PO (Cost Controlled Cascaded Prediction Optimization), a self-supervised framework for optimizing LLM cascades under probabilistic cost constraints. By focusing on minimizing regret with respect to the most powerful model (MPM), C3PO avoids the need for labeled data by constructing a cascade using only unlabeled model outputs. It leverages conformal prediction to bound the probability that inference cost exceeds a user-specified budget. We provide theoretical guarantees on both cost control and generalization error, and show that our optimization procedure is effective even with small calibration sets. Empirically, C3PO achieves state-of-the-art performance across a diverse set of reasoning benchmarks including GSM8K, MATH-500, BigBench-Hard and AIME, outperforming strong LLM cascading baselines in both accuracy and cost-efficiency. Our results demonstrate that principled, label-free cascade optimization can enable scalable LLM deployment.

Large Language Models (LLMs) have advanced the automated generation of code from natural language prompts. However, low-resource languages (LRLs) like Bangla remain underrepresented due to the limited availability of instruction-to-code datasets and evaluation benchmarks. To address this, the BLP Workshop at IJCNLP-AACL 2025 introduced a shared task on "Code Generation in Bangla". In this work, we propose a method that combines instruction prompting with a test-driven, feedback-guided iterative refinement process using a fine-tuned Qwen2.5-14B model. The model generates code from Bangla instructions, tests it against unit tests, and iteratively refines any failing outputs through three evaluation passes, using test feedback to guide each step. This approach helped our team "Retriv" to secure 2nd place in the shared task with a Pass@1 score of 0.934. The analysis highlights challenges in Bangla instruction understanding and Python code generation, emphasizing the need for targeted methods in LRLs. We made experimental scripts publicly available for the community.

Reliability and failure detection of large language models (LLMs) is critical for their deployment in high-stakes, multi-step reasoning tasks. Prior work explores confidence estimation for self-evaluating LLM-scorer systems, with confidence scorers estimating the likelihood of errors in LLM responses. However, most methods focus on single-step outputs and overlook the challenges of multi-step reasoning. In this work, we extend self-evaluation techniques to multi-step tasks, testing two intuitive approaches: holistic scoring and step-by-step scoring. Using two multi-step benchmark datasets, we show that stepwise evaluation generally outperforms holistic scoring in detecting potential errors, with up to 15% relative increase in AUC-ROC. Our findings demonstrate that self-evaluating LLM systems provide meaningful confidence estimates in complex reasoning, improving their trustworthiness and providing a practical framework for failure detection.

Infrared imagery enables temperature-based scene understanding using passive sensors, particularly under conditions of low visibility where traditional RGB imaging fails. Yet, developing downstream vision models for infrared applications is hindered by the scarcity of high-quality annotated data, due to the specialized expertise required for infrared annotation. While synthetic infrared image generation has the potential to accelerate model development by providing large-scale, diverse training data, training foundation-level generative diffusion models in the infrared domain has remained elusive due to limited datasets. In light of such data constraints, we explore an inference-time scaling approach using a domain-adapted CLIP-based verifier for enhanced infrared image generation quality. We adapt FLUX.1-dev, a state-of-the-art text-to-image diffusion model, to the infrared domain by finetuning it on a small sample of infrared images using parameter-efficient techniques. The trained verifier is then employed during inference to guide the diffusion sampling process toward higher quality infrared generations that better align with input text prompts. Empirically, we find that our approach leads to consistent improvements in generation quality, reducing FID scores on the KAIST Multispectral Pedestrian Detection Benchmark dataset by 10% compared to unguided baseline samples. Our results suggest that inference-time guidance offers a promising direction for bridging the domain gap in low-data infrared settings.

Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements. While large datasets exist for web and mobile interactions, high-quality resources for desktop environments are limited. CUA, a large-scale desktop grounding dataset built from expert human demonstrations. It covers 87 applications across 12 categories and includes 56K screenshots, with every on-screen element carefully annotated for a total of over 3.56M human-verified annotations. From these demonstrations, we generate diverse instructions that capture a wide range of real-world tasks, providing high-quality data for model training. These results demonstrate the critical role of high-quality, expert-driven datasets in advancing general-purpose computer-use agents. The vision of computer-use agents (CUA) that operate software on behalf of users has gained significant momentum with recent progress in multimodal large language model-based agents (OpenAI, 2025; Anthropic, 2024a; Qin et al., 2025; Wang et al., 2025a). These agents promise to automate routine work and make complex digital tools more accessible. For such agents to succeed, they must first plan the next step in a task, then ground the plan to the exact on-screen element to click, type, or drag. Accurate grounding is critical: without correctly identifying the right button or menu item, even a flawless plan cannot be executed. In FreeCAD, for instance, when asked to "open the color picker" (Figure 1), the agent must distinguish a small palette icon from look-alike tools, one of which it must precisely click. When grounding fails, the plan quickly veers off course, minor errors compound, and tasks ultimately fail (Nayak et al., 2025). Moreover, grounding in desktop applications is challenging due to their complexity and diversity. These applications often feature high-resolution displays with dense layouts and visually similar elements, making precise localization difficult.

Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most existing RAG methods focus on single-step retrieval, which is often insufficient for answering complex questions that require multi-step search. Recently, multi-step retrieval approaches have emerged, typically involving the fine-tuning of small LLMs to perform multi-step retrieval. This type of fine-tuning is highly resource-intensive and does not enable the use of larger LLMs. In this work, we propose Q-RAG, a novel approach that fine-tunes the Em-bedder model for multi-step retrieval using reinforcement learning (RL). Q-RAG offers a competitive, resource-efficient alternative to existing multi-step retrieval methods for open-domain question answering and achieves state-of-the-art results on the popular long-context benchmarks Babilong and RULER for contexts up to 10M tokens. Large language models (LLMs) have achieved impressive results across a wide range of tasks (Novikov et al., 2025; Guo et al., 2025; Y ang et al., 2025). However, they still face some several fundamental limitations such as static knowledge, computational inefficiency on long contexts, degraded performance caused by attention dilution, and hallucinations (Hsieh et al., 2024; Kuratov et al., 2024; Liu et al., 2025).

We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language models (LMs). RLVE enables each verifiable environment to dynamically adapt its problem difficulty distribution to the policy model's capabilities as training progresses. In contrast, static data distributions often lead to vanishing learning signals when problems are either too easy or too hard for the policy. To implement RLVE, we create RLVE-Gym, a large-scale suite of 400 verifiable environments carefully developed through manual environment engineering. Using RLVE-Gym, we show that environment scaling, i.e., expanding the collection of training environments, consistently improves generalizable reasoning capabilities. RLVE with joint training across all 400 environments in RLVE-Gym yields a 3.37% absolute average improvement across six reasoning benchmarks, starting from one of the strongest 1.5B reasoning LMs. By comparison, continuing this LM's original RL training yields only a 0.49% average absolute gain despite using over 3x more compute. We release our code publicly.

Automatic ICD coding, the task of assigning disease and procedure codes to electronic medical records, is crucial for clinical documentation and billing. While existing methods primarily enhance model understanding of code hierarchies and synonyms, they often overlook the pervasive use of medical acronyms in clinical notes, a key factor in ICD code inference. To address this gap, we propose a novel effective data augmentation technique that leverages large language models to expand medical acronyms, allowing models to be trained on their full form representations. Moreover, we incorporate consistency training to regularize predictions by enforcing agreement between the original and augmented documents. Extensive experiments on the MIMIC-III dataset demonstrate that our approach, ACE-ICD establishes new state-of-the-art performance across multiple settings, including common codes, rare codes, and full-code assignments. Our code is publicly available.

Low-dose computed tomography (CT) represents a significant improvement in patient safety through lower radiation doses, but increased noise, blur, and contrast loss can diminish diagnostic quality. Therefore, consistency and robustness in image quality assessment become essential for clinical applications. In this study, we propose an LLM-based quality assessment system that generates both numerical scores and textual descriptions of degradations such as noise, blur, and contrast loss. Furthermore, various inference strategies - from the zero-shot approach to metadata integration and error feedback - are systematically examined, demonstrating the progressive contribution of each method to overall performance. The resultant assessments yield not only highly correlated scores but also interpretable output, thereby adding value to clinical workflows. The source codes of our study are available at https://github.com/itu-biai/lmms_ldct_iqa.