Related papers: ARC-AGI-2 Technical Report
We present Agentic Retrieval-Augmented Code Synthesis (ARCS), a system that improves LLM-based code generation without fine-tuning. ARCS operates through a budgeted synthesize-execute-repair loop over a frozen model: it retrieves relevant…
We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their interactions in-context. While prior work has studied…
An extension of Transformers is proposed that enables explicit relational reasoning through a novel module called the Abstractor. At the core of the Abstractor is a variant of attention called relational cross-attention. The approach is…
Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider…
Recent advancements in reasoning have significantly enhanced the capabilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) across diverse tasks. However, excessive reliance on chain-of-thought (CoT) reasoning…
Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and…
Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using…
In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance. To alleviate such data size…
Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while…
Tool-Integrated Reasoning (TIR) has significantly enhanced the capabilities of Large Language Models (LLMs), yet current agents tend to exhibit cognitive offloading, redundantly invoking external tools even for simple tasks. In this paper,…
Reasoning requires going beyond pattern matching or memorization of solutions to identify and implement "algorithmic procedures" that can be used to deduce answers to hard problems. Doing so requires realizing the most relevant primitives,…
A number of problems in the processing of sound and natural language, as well as in other areas, can be reduced to simultaneously reading an input sequence and writing an output sequence of generally different length. There are well…
Large Language Models (LLMs) that can continually improve beyond their training budgets are able to solve increasingly difficult problems by adapting at test time, a property we refer to as extrapolation. However, standard reinforcement…
Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require…
Non-autoregressive automatic speech recognition (ASR) modeling has received increasing attention recently because of its fast decoding speed and superior performance. Among representatives, methods based on the connectionist temporal…
A long-held objective in AI is to build systems that understand concepts in a humanlike way. Setting aside the difficulty of building such a system, even trying to evaluate one is a challenge, due to present-day AI's relative opacity and…
Artificial Intelligence (AI) has achieved remarkable success in specialized tasks but struggles with efficient skill acquisition and generalization. The Abstraction and Reasoning Corpus (ARC) benchmark evaluates intelligence based on…
We propose a new method to measure the task-specific accuracy of Retrieval-Augmented Large Language Models (RAG). Evaluation is performed by scoring the RAG on an automatically-generated synthetic exam composed of multiple choice questions…
Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce…
Agentic AI systems increasingly act through tools, sub-agents, and external services, but governance controls are still commonly attached to prompts, dashboards, or post-hoc documentation. This creates a structural mismatch in regulated…