Related papers: Platonic Representations for Poverty Mapping: Unif…
Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs.…
We present a solver-agnostic framework in which coordinated large language model (LLM) agents autonomously execute the complete computational mechanics workflow, from perceptual data of an engineering component through geometry extraction,…
Wealth transactions are central to economic activity, and their particularities shape macroeconomic outcomes. We propose an agent-based model to investigate how homophily influences economic inequality. The model simulates wealth exchanges…
Large language models are increasingly deployed as autonomous coding agents and have achieved remarkably strong performance on software engineering benchmarks. However, it is unclear whether such success transfers to computational…
Vision-and-Language Navigation (VLN) requires an agent to navigate in a real-world environment following natural language instructions. From both the textual and visual perspectives, we find that the relationships among the scene, its…
Recent advances in the intrinsic reasoning capabilities of large language models (LLMs) have given rise to LLM-based agent systems that exhibit near-human performance on a variety of automated tasks. However, although these systems share…
Ad hoc dataset search requires matching underspecified natural-language queries against sparse, heterogeneous metadata records, a task where typical lexical or dense retrieval alone falls short. We reposition dataset search as a…
Traditional augmented reality (AR) systems predominantly rely on fixed class detectors or fiducial markers, limiting their ability to interpret complex, open-vocabulary natural language queries. We present a modular AR agent system that…
The rapid proliferation of online misinformation threatens the stability of digital social systems and poses significant risks to public trust, policy, and safety, necessitating reliable automated fake news detection. Existing methods often…
What information is sufficient to learn the full richness of human scene understanding? The distributional hypothesis holds that the statistical co-occurrence of language and images captures the conceptual knowledge underlying visual…
Large language models (LLMs) produce high-dimensional embeddings that capture rich semantic and syntactic relationships between words, sentences, and concepts. Investigating the topological structures of LLM embedding spaces via mapper…
Large Language Models (LLMs) have demonstrated unprecedented language understanding and reasoning capabilities to capture diverse user preferences and advance personalized recommendations. Despite the growing interest in LLM-based…
We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large language models. The system runs two coupled loops: (1) explanation refinement, where an…
Extracting alphanumeric data from form-like documents such as invoices, purchase orders, bills, and financial documents is often performed via vision (OCR) and learning algorithms or monolithic pipelines with limited potential for systemic…
Large language models (LLMs) often achieve high performance in native language identification (NLI) benchmarks by leveraging superficial contextual clues such as names, locations, and cultural stereotypes, rather than the underlying…
Multimodal Large Language Models (MLLMs) have shown remarkable versatility but face challenges in demonstrating true visual understanding, particularly in chart reasoning tasks. Existing benchmarks like ChartQA reveal significant reliance…
The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the world. Recent work exploits this convergence by aligning frozen pretrained vision and…
The Strong Platonic Representation Hypothesis suggests that representational convergence in artificial neural networks can be harnessed constructively: embeddings can be translated across models through a universal latent space without…
Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to associate objects with their properties and spatial relations. Yet it remains unclear where and how such associations…
As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard to disentangle agentic reasoning when evaluated in complex…