English
Related papers

Related papers: ARC-AGI-2 Technical Report

200 papers

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…

Software Engineering · Computer Science 2025-10-28 Manish Bhattarai , Miguel Cordova , Minh Vu , Javier Santos , Ismael Boureima , Dan O'Malley

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…

Computation and Language · Computer Science 2026-02-26 Eric Todd , Jannik Brinkmann , Rohit Gandikota , David Bau

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…

Machine Learning · Statistics 2024-04-16 Awni Altabaa , Taylor Webb , Jonathan Cohen , John Lafferty

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…

Computer Vision and Pattern Recognition · Computer Science 2021-01-27 Nicola Messina , Fabrizio Falchi , Andrea Esuli , Giuseppe Amato

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…

Computation and Language · Computer Science 2025-05-22 Jinghui Lu , Haiyang Yu , Siliang Xu , Shiwei Ran , Guozhi Tang , Siqi Wang , Bin Shan , Teng Fu , Hao Feng , Jingqun Tang , Han Wang , Can Huang

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…

Computation and Language · Computer Science 2026-01-12 Jiawei Shen , Jia Zhu , Hanghui Guo , Weijie Shi , Yue Cui , Qingyu Niu , Guoqing Ma , Yidan Liang , Jingjiang Liu , Yiling Wang , Shimin Di , Jiajie Xu

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…

Artificial Intelligence · Computer Science 2025-05-22 Haotian Luo , Haiying He , Yibo Wang , Jinluan Yang , Rui Liu , Naiqiang Tan , Xiaochun Cao , Dacheng Tao , Li Shen

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…

Computation and Language · Computer Science 2020-10-06 Dongqin Xu , Junhui Li , Muhua Zhu , Min Zhang , Guodong Zhou

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…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Muhammad Maaz , Hanoona Rasheed , Fahad Shahbaz Khan , Salman Khan

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,…

Computation and Language · Computer Science 2026-01-22 Zhaiyu Fang , Ruipeng Sun

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,…

Artificial Intelligence · Computer Science 2025-10-03 Yuxiao Qu , Anikait Singh , Yoonho Lee , Amrith Setlur , Ruslan Salakhutdinov , Chelsea Finn , Aviral Kumar

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…

Machine Learning · Computer Science 2022-02-17 Grzegorz Rypeść , Łukasz Lepak , Paweł Wawrzyński

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…

Machine Learning · Computer Science 2026-03-24 Ian Wu , Yuxiao Qu , Amrith Setlur , Aviral Kumar

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…

Computation and Language · Computer Science 2026-01-21 Guo Chen , Junjie Huang , Huaijin Xie , Fei Sun , Tao Jia

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…

Computation and Language · Computer Science 2022-10-13 Ke-Han Lu , Kuan-Yu Chen

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 · Computer Science 2022-06-29 Victor Vikram Odouard , Melanie Mitchell

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…

Artificial Intelligence · Computer Science 2025-05-05 Sébastien Ferré

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…

Computation and Language · Computer Science 2024-05-24 Gauthier Guinet , Behrooz Omidvar-Tehrani , Anoop Deoras , Laurent Callot

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…

Computation and Language · Computer Science 2026-05-22 Qisheng Su , Zhen Fang , Shiting Huang , Yu Zeng , Yiming Zhao , Kou Shi , Ziao Zhang , Lin Chen , Zehui Chen , Lijun Wu , Feng Zhao

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…

Software Engineering · Computer Science 2026-05-11 Gaston Besanson