Related papers: ARC Prize 2025: Technical Report

Retrieval-augmented generation (RAG) is a framework enabling large language models (LLMs) to enhance their accuracy and reduce hallucinations by integrating external knowledge bases. In this paper, we introduce a hybrid RAG system enhanced…

As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation. We demonstrate that standard "LLM-as-a-Judge" protocols suffer from a systematic…

This work establishes a foundational framework for standardizing AI evaluation RCTs (sometimes called human uplift studies). Drawing on established experimental practices from disciplines with established RCT traditions, including software…

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged…

The integration of large language models (LLMs) into peer review raises a concern beyond authorship and detection: the potential cascading automation of the entire editorial process. As reviews become partially or fully machine-generated,…

Numerous studies have assessed the proficiency of AI systems, particularly large language models (LLMs), in facilitating everyday tasks such as email writing, question answering, and creative content generation. However, researchers face…

Automatic Speech Recognition (ASR) is an integral component of modern technology, powering applications such as voice-activated assistants, transcription services, and accessibility tools. Yet ASR systems continue to struggle with the…

Large reasoning language models are typically run with fixed inference budgets, which can waste computation or terminate reasoning prematurely. We introduce Certainty-Guided Reasoning (CGR), a model-agnostic adaptive inference procedure…

Large language models (LLMs) exhibit remarkable problem-solving abilities, but struggle with complex tasks due to static internal knowledge. Retrieval-Augmented Generation (RAG) enhances access to external information, yet remains limited…

AI model documentation is fragmented across platforms and inconsistent in structure, preventing policymakers, auditors, and users from reliably assessing safety claims, data provenance, and version-level changes. We analyzed documentation…

Building general-purpose reasoning models using reinforcement learning with verifiable rewards (RLVR) across diverse domains has been widely adopted by frontier open-weight models. However, their training recipes and domain mixtures are…

The spreading of AI-generated images (AIGI), driven by advances in generative AI, poses a significant threat to information security and public trust. Existing AIGI detectors, while effective against images in clean laboratory settings,…

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing…

Information tasks such as writing surveys or analytical reports require complex search and reasoning, and have recently been grouped under the umbrella of \textit{deep research} -- a term also adopted by recent models targeting these…

This paper presents mRAG, a multi-agent retrieval-augmented generation (RAG) framework composed of specialized agents for subtasks such as planning, searching, reasoning, and coordination. Our system uses a self-training paradigm with…

While Retrieval-Augmented Generation (RAG) mitigates hallucination and knowledge staleness in Large Language Models (LLMs), existing frameworks often falter on complex, multi-hop queries that require synthesizing information from disparate…

Conventional wisdom in the age of LLMs dictates that solving IQ-test-like visual puzzles from the ARC-AGI-1 benchmark requires capabilities derived from massive pretraining. To counter this, we introduce CompressARC, a 76K parameter model…

The LiveRAG Challenge at SIGIR 2025, held between March and May 2025, provided a competitive platform for advancing Retrieval-Augmented Generation (RAG) technologies. Participants from academia and industry were invited to develop a…

While AI innovation accelerates rapidly, the intellectual process behind breakthroughs -- how researchers identify gaps, synthesize prior work, and generate insights -- remains poorly understood. The lack of structured data on scientific…

Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent…