Related papers: MATATA: Weakly Supervised End-to-End MAthematical …

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

Tabular foundation models are becoming increasingly popular for low-resource tabular problems. These models make up for small training datasets by pretraining on large volumes of synthetic data. The prior knowledge obtained via pretraining…

Visual analytics (VA) requires analysts to iteratively propose analysis tasks based on observations and execute tasks by creating visualizations and interactive exploration to gain insights. This process demands skills in programming, data…

Large language models (LLMs) demonstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global planning, often leading to redundant or inaccurate reasoning.…

Large Language Model (LLM)-based agents have recently shown impressive capabilities in complex reasoning and tool use via multi-step interactions with their environments. While these agents have the potential to tackle complicated tasks,…

Table reasoning tasks have shown remarkable progress with the development of large language models (LLMs), which involve interpreting and drawing conclusions from tabular data based on natural language (NL) questions. Existing solutions…

Solving complex reasoning tasks may involve visual understanding, domain knowledge retrieval, numerical calculation, and multi-step reasoning. Existing methods augment large language models (LLMs) with external tools but are restricted to…

Tool-augmented Large Language Models (TALMs) are known to enhance the skillset of large language models (LLMs), thereby, leading to their improved reasoning abilities across many tasks. While, TALMs have been successfully employed in…

Temporal reasoning over tabular data presents substantial challenges for large language models (LLMs), as evidenced by recent research. In this study, we conduct a comprehensive analysis of temporal datasets to pinpoint the specific…

Multi-agent systems (MAS) often achieve higher reasoning accuracy than single models, but their reliance on repeated debates across agents makes them computationally expensive. We introduce SMAGDi, a distillation framework that transfers…

Vision-language-action (VLA) reasoning tasks require agents to interpret multimodal instructions, perform long-horizon planning, and act adaptively in dynamic environments. Existing approaches typically train VLA models in an end-to-end…

Recent advancements in generative Large Language Models(LLMs) have been remarkable, however, the quality of the text generated by these models often reveals persistent issues. Evaluating the quality of text generated by these models,…

Large Reasoning Models (LRMs) have revolutionized complex problem-solving, yet they exhibit a pervasive "overthinking", generating unnecessarily long reasoning chains. While current solutions improve token efficiency, they often sacrifice…

Spreadsheets are central to real-world applications such as enterprise reporting, auditing, and scientific data management. Despite their ubiquity, existing large language model based approaches typically treat tables as plain text,…

Large language models (LLMs) have exhibited impressive multilingual reasoning capabilities, driven by extensive multilingual pre-training corpora and instruction fine-tuning data. However, a performance gap exists between high- and…

Large Language Models (LLMs) suffer from hallucinations and factual inaccuracies, especially in complex reasoning and fact verification tasks. Multi-Agent Debate (MAD) systems aim to improve answer accuracy by enabling multiple LLM agents…

Recent VLM-based agents aim to replicate OpenAI O3's "thinking with images" via tool use, yet most open-source methods restrict inputs to a single image, limiting their applicability to real-world multi-image QA tasks. To address this gap,…

This paper proposes a detailed prompting flow, termed Table-Logic, to investigate the performance contrasts between bigger and smaller language models (LMs) utilizing step-by-step reasoning methods in the TableQA task. The method processes…

Large language models (LLMs) can reshape information processing by handling data analysis, visualization, and interpretation in an interactive, context-aware dialogue with users, including voice interaction, while maintaining high…

Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world…