Archives AI News

arXiv:2503.15108v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this paper, we introduce VIPER, a novel framework for multimodal instruction-based planning that integrates VLM-based perception with LLM-based reasoning. Our approach uses a modular pipeline where a frozen VLM generates textual descriptions of image observations, which are then processed by an LLM policy to predict actions based on the task goal. We fine-tune the reasoning module using behavioral cloning and reinforcement learning, improving our agent's decision-making capabilities. Experiments on the ALFWorld benchmark show that VIPER significantly outperforms state-of-the-art visual instruction-based planners while narrowing the gap with purely text-based oracles. By leveraging text as an intermediate representation, VIPER also enhances explainability, paving the way for a fine-grained analysis of perception and reasoning components.

arXiv:2509.05378v1 Announce Type: new Abstract: In medical coding, experts map unstructured clinical notes to alphanumeric codes for diagnoses and procedures. We introduce Code Like Humans: a new agentic framework for medical coding with large language models. It implements official coding guidelines for human experts, and it is the first solution that can support the full ICD-10 coding system (+70K labels). It achieves the best performance to date on rare diagnosis codes (fine-tuned discriminative classifiers retain an advantage for high-frequency codes, to which they are limited). Towards future work, we also contribute an analysis of system performance and identify its `blind spots' (codes that are systematically undercoded).

arXiv:2509.05381v1 Announce Type: new Abstract: Large language models are increasingly aligned to human preferences through reinforcement learning from human feedback (RLHF) and related methods such as Direct Preference Optimization (DPO), Constitutional AI, and RLAIF. While effective, these methods exhibit recurring failure patterns i.e., reward hacking, sycophancy, annotator drift, and misgeneralization. We introduce the concept of the Alignment Gap, a unifying lens for understanding recurring failures in feedback-based alignment. Using a KL-tilting formalism, we illustrate why optimization pressure tends to amplify divergence between proxy rewards and true human intent. We organize these failures into a catalogue of Murphys Laws of AI Alignment, and propose the Alignment Trilemma as a way to frame trade-offs among optimization strength, value capture, and generalization. Small-scale empirical studies serve as illustrative support. Finally, we propose the MAPS framework (Misspecification, Annotation, Pressure, Shift) as practical design levers. Our contribution is not a definitive impossibility theorem but a perspective that reframes alignment debates around structural limits and trade-offs, offering clearer guidance for future design.

arXiv:2509.05363v1 Announce Type: new Abstract: We introduce SasAgent, a multi-agent AI system powered by large language models (LLMs) that automates small-angle scattering (SAS) data analysis by leveraging tools from the SasView software and enables user interaction via text input. SasAgent features a coordinator agent that interprets user prompts and delegates tasks to three specialized agents for scattering length density (SLD) calculation, synthetic data generation, and experimental data fitting. These agents utilize LLM-friendly tools to execute tasks efficiently. These tools, including the model data tool, Retrieval-Augmented Generation (RAG) documentation tool, bump fitting tool, and SLD calculator tool, are derived from the SasView Python library. A user-friendly Gradio-based interface enhances user accessibility. Through diverse examples, we demonstrate SasAgent's ability to interpret complex prompts, calculate SLDs, generate accurate scattering data, and fit experimental datasets with high precision. This work showcases the potential of LLM-driven AI systems to streamline scientific workflows and enhance automation in SAS research.

arXiv:2509.05375v1 Announce Type: new Abstract: While prompt engineering has emerged as a crucial technique for optimizing large language model performance, the underlying optimization landscape remains poorly understood. Current approaches treat prompt optimization as a black-box problem, applying sophisticated search algorithms without characterizing the landscape topology they navigate. We present a systematic analysis of fitness landscape structures in prompt engineering using autocorrelation analysis across semantic embedding spaces. Through experiments on error detection tasks with two distinct prompt generation strategies -- systematic enumeration (1,024 prompts) and novelty-driven diversification (1,000 prompts) -- we reveal fundamentally different landscape topologies. Systematic prompt generation yields smoothly decaying autocorrelation, while diversified generation exhibits non-monotonic patterns with peak correlation at intermediate semantic distances, indicating rugged, hierarchically structured landscapes. Task-specific analysis across 10 error detection categories reveals varying degrees of ruggedness across different error types. Our findings provide an empirical foundation for understanding the complexity of optimization in prompt engineering landscapes.

arXiv:2509.05346v1 Announce Type: new Abstract: While Large Language Models (LLMs) are increasingly envisioned as intelligent assistants for personalized learning, systematic head-to-head evaluations within authentic learning scenarios remain limited. This study conducts an empirical comparison of three state-of-the-art LLMs on a tutoring task that simulates a realistic learning setting. Using a dataset comprising a student's answers to ten questions of mixed formats with correctness labels, each LLM is required to (i) analyze the quiz to identify underlying knowledge components, (ii) infer the student's mastery profile, and (iii) generate targeted guidance for improvement. To mitigate subjectivity and evaluator bias, we employ Gemini as a virtual judge to perform pairwise comparisons along various dimensions: accuracy, clarity, actionability, and appropriateness. Results analyzed via the Bradley-Terry model indicate that GPT-4o is generally preferred, producing feedback that is more informative and better structured than its counterparts, while DeepSeek-V3 and GLM-4.5 demonstrate intermittent strengths but lower consistency. These findings highlight the feasibility of deploying LLMs as advanced teaching assistants for individualized support and provide methodological guidance for future empirical research on LLM-driven personalized learning.

arXiv:2509.05330v1 Announce Type: new Abstract: Automatic emotion recognition has become increasingly important with the rise of AI, especially in fields like healthcare, education, and automotive systems. However, there is a lack of multimodal datasets, particularly involving body motion and physiological signals, which limits progress in the field. To address this, the MVRS dataset is introduced, featuring synchronized recordings from 13 participants aged 12 to 60 exposed to VR based emotional stimuli (relaxation, fear, stress, sadness, joy). Data were collected using eye tracking (via webcam in a VR headset), body motion (Kinect v2), and EMG and GSR signals (Arduino UNO), all timestamp aligned. Participants followed a unified protocol with consent and questionnaires. Features from each modality were extracted, fused using early and late fusion techniques, and evaluated with classifiers to confirm the datasets quality and emotion separability, making MVRS a valuable contribution to multimodal affective computing.

arXiv:2509.05325v1 Announce Type: new Abstract: Artificial intelligence (AI) is transforming supply chain management, yet progress in predictive tasks -- such as delivery delay prediction -- remains constrained by the scarcity of high-quality, openly available datasets. Existing datasets are often proprietary, small, or inconsistently maintained, hindering reproducibility and benchmarking. We present SynDelay, a synthetic dataset designed for delivery delay prediction. Generated using an advanced generative model trained on real-world data, SynDelay preserves realistic delivery patterns while ensuring privacy. Although not entirely free of noise or inconsistencies, it provides a challenging and practical testbed for advancing predictive modelling. To support adoption, we provide baseline results and evaluation metrics as initial benchmarks, serving as reference points rather than state-of-the-art claims. SynDelay is publicly available through the Supply Chain Data Hub, an open initiative promoting dataset sharing and benchmarking in supply chain AI. We encourage the community to contribute datasets, models, and evaluation practices to advance research in this area. All code is openly accessible at https://supplychaindatahub.org.

arXiv:2506.23273v2 Announce Type: replace Abstract: Despite the advancements of large language models, text2sql still faces many challenges, particularly with complex and domain-specific queries. In finance, database designs and financial reporting layouts vary widely between financial entities and countries, making text2sql even more challenging. We present FinStat2SQL, a lightweight text2sql pipeline enabling natural language queries over financial statements. Tailored to local standards like VAS, it combines large and small language models in a multi-agent setup for entity extraction, SQL generation, and self-correction. We build a domain-specific database and evaluate models on a synthetic QA dataset. A fine-tuned 7B model achieves 61.33% accuracy with sub-4-second response times on consumer hardware, outperforming GPT-4o-mini. FinStat2SQL offers a scalable, cost-efficient solution for financial analysis, making AI-powered querying accessible to Vietnamese enterprises.

arXiv:2509.05469v1 Announce Type: new Abstract: Realistic visual renderings of street-design scenarios are essential for public engagement in active transportation planning. Traditional approaches are labor-intensive, hindering collective deliberation and collaborative decision-making. While AI-assisted generative design shows transformative potential by enabling rapid creation of design scenarios, existing generative approaches typically require large amounts of domain-specific training data and struggle to enable precise spatial variations of design/configuration in complex street-view scenes. We introduce a multi-agent system that edits and redesigns bicycle facilities directly on real-world street-view imagery. The framework integrates lane localization, prompt optimization, design generation, and automated evaluation to synthesize realistic, contextually appropriate designs. Experiments across diverse urban scenarios demonstrate that the system can adapt to varying road geometries and environmental conditions, consistently yielding visually coherent and instruction-compliant results. This work establishes a foundation for applying multi-agent pipelines to transportation infrastructure planning and facility design.