English
Related papers

Related papers: HiL-Bench (Human-in-Loop Benchmark): Do Agents Kno…

200 papers

Large Language Model (LLM) based agents excel at general reasoning but often fail in specialized domains where success hinges on long-tail knowledge absent from their training data. While human experts can provide this missing knowledge,…

Artificial Intelligence · Computer Science 2026-02-27 Zhiming Wang , Jinwei He , Feng Lu

The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…

Artificial Intelligence · Computer Science 2026-01-15 Logan Ritchie , Sushant Mehta , Nick Heiner , Mason Yu , Edwin Chen

Faces and humans are crucial elements in social interaction and are widely included in everyday photos and videos. Therefore, a deep understanding of faces and humans will enable multi-modal assistants to achieve improved response quality…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Lixiong Qin , Shilong Ou , Miaoxuan Zhang , Jiangning Wei , Yuhang Zhang , Xiaoshuai Song , Yuchen Liu , Mei Wang , Weiran Xu

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…

We introduce ISO-Bench, a benchmark for coding agents to test their capabilities on real-world inference optimization tasks. These tasks were taken from vLLM and SGLang, two of the most popular LLM serving frameworks. Each task provides an…

Machine Learning · Computer Science 2026-02-24 Ayush Nangia , Shikhar Mishra , Aman Gokrani , Paras Chopra

Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably compute with distributed information, rather than merely…

Multiagent Systems · Computer Science 2026-04-15 Yuzhe Zhang , Feiran Liu , Yi Shan , Xinyi Huang , Xin Yang , Yueqi Zhu , Xuxin Cheng , Cao Liu , Ke Zeng , Terry Jingchen Zhang , Wenyuan Jiang

Existing benchmarks for Large Language Model (LLM) agents focus on task completion under idealistic settings but overlook reliability in real-world, user-facing applications. In domains, such as in-car voice assistants, users often issue…

Artificial Intelligence · Computer Science 2026-01-30 Johannes Kirmayr , Lukas Stappen , Elisabeth André

In a Human-in-the-Loop paradigm, a robotic agent is able to act mostly autonomously in solving a task, but can request help from an external expert when needed. However, knowing when to request such assistance is critical: too few requests…

As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard for humans to generate…

State-of-the-art reasoning LLMs are powerful problem solvers, but they still occasionally make mistakes. However, adopting AI models in risk-sensitive domains often requires error rates near 0%. To address this gap, we propose collaboration…

Artificial Intelligence · Computer Science 2025-07-22 Michael J. Zellinger , Matt Thomson

AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which…

Effective collaboration begins with knowing when to ask for help. For example, when trying to identify an occluded object, a human would ask someone to remove the obstruction. Can MLLMs exhibit a similar "proactive" behavior by requesting…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Thomas De Min , Subhankar Roy , Stéphane Lathuilière , Elisa Ricci , Massimiliano Mancini

As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests…

Software Engineering · Computer Science 2026-05-21 Bingchen Zhao , Dhruv Srikanth , Yuxiang Wu , Zhengyao Jiang

We introduce the first version of KWBench (Knowledge Work Bench), a benchmark for unprompted problem recognition in large language models: can an LLM identify a professional scenario before attempting to solve it. Existing frontier…

Artificial Intelligence · Computer Science 2026-04-20 Ankit Maloo

Coding agents are increasingly deployed to autonomously maintain software, including to resolve user-reported issues: a bug report comes in and the agent creates a patch to address it. However, in any real-world deployment, they will…

Software Engineering · Computer Science 2026-05-11 Thibaud Gloaguen , Niels Mündler , Mark Müller , Veselin Raychev , Martin Vechev

Human-robot interaction (HRI) has long studied how agents and people coordinate to achieve shared goals. In this work, we formalize and benchmark the non-intrusive assistance as an independent paradigm of HRI, where a robot proactively…

Robotics · Computer Science 2026-05-05 Yuedi Zhang , Shuanghao Bai , Wanqi Zhou , Haoran Zhang , Qi Zhang , Zhirong Luan , Badong Chen

Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks,…

Equipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone. However, the effective execution of these tools…

Computation and Language · Computer Science 2026-04-30 Wenxuan Wang , Juluan Shi , Zixuan Ling , Yuk-Kit Chan , Chaozheng Wang , Cheryl Lee , Youliang Yuan , Jen-tse Huang , Wenxiang Jiao , Michael R. Lyu

Humans know when to reach for help e.g. $347 \times 28$ warrants a calculator while $2+2$ does not. Language models do not. Prompt-based approaches can instruct a model when to invoke tools, but this scaffolding does not teach it to…

Machine Learning · Computer Science 2026-05-28 Abhijit Kumar , Zoey Wu , Mohit Suley

Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…

‹ Prev 1 2 3 10 Next ›