English
Related papers

Related papers: Auto Researching, not hyperparameter tuning: Conve…

200 papers

Automated essay scoring (AES) systems increasingly rely on large language models, yet little is known about how architectural choices shape their performance across different essay quality levels. This paper evaluates single-agent and…

Computation and Language · Computer Science 2026-02-02 Jamiu Adekunle Idowu , Ahmed Almasoud

AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effective lifelong memory requires navigating a vast design space…

Artificial Intelligence · Computer Science 2026-04-03 Jiaqi Liu , Zipeng Ling , Shi Qiu , Yanqing Liu , Siwei Han , Peng Xia , Haoqin Tu , Zeyu Zheng , Cihang Xie , Charles Fleming , Mingyu Ding , Huaxiu Yao

The adoption of large language models (LLMs) for structured information extraction from financial documents has accelerated rapidly, yet production deployments face fundamental architectural decisions with limited empirical guidance. We…

Artificial Intelligence · Computer Science 2026-03-25 Siddhant Kulkarni , Yukta Kulkarni

When deploying LLMs in agentic architectures requiring real-time decisions under temporal constraints, we assume they reliably determine whether action windows remain open or have closed. This assumption is untested. We characterize…

Computation and Language · Computer Science 2025-11-17 Javier Marín

Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of training data. Large language models (LLMs) have recently…

Scenario mining from extensive autonomous driving datasets, such as Argoverse 2, is crucial for the development and validation of self-driving systems. The RefAV framework represents a promising approach by employing Large Language Models…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Yifei Chen , Ross Greer

LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their assessments, and if so, how many are needed? Through 960 sessions with two model pairs across 15…

Artificial Intelligence · Computer Science 2026-04-02 HyunJoon Jung , William Na

While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constraint that applicable law must match the temporal context of each case, as retroactive…

Computation and Language · Computer Science 2026-05-26 Wei Fan , Yining Zhou , Mufan Zhang , Yanbing Weng , Yiran HU , Tianshi Zheng , Baixuan Xu , Chunyang Li , Jianhui Yang , Haoran Li , Yangqiu Song

LLMs generate buggy code: 29.6% of SWE-bench solved patches fail, 62% of BaxBench solutions have vulnerabilities, and existing tools only catch 65% of bugs with 35% false positives. We built CodeX-Verify, a multi-agent system that uses four…

Software Engineering · Computer Science 2025-12-05 Shreshth Rajan

LLM-based agents are assumed to integrate environmental observations into their reasoning: discovering highly relevant but unexpected information should naturally lead to a model exploiting its own discoveries. We show that this assumption…

Computation and Language · Computer Science 2026-04-21 Leon Engländer , Sophia Althammer , Ahmet Üstün , Matthias Gallé , Tom Sherborne

A major challenge in autonomous vehicle research is modeling agent behaviors, which has critical applications including constructing realistic and reliable simulations for off-board evaluation and forecasting traffic agents motion for…

Artificial Intelligence · Computer Science 2024-09-30 Zhenghao Peng , Wenjie Luo , Yiren Lu , Tianyi Shen , Cole Gulino , Ari Seff , Justin Fu

Multi-agent systems built on large language models (LLMs) are expected to enhance decision-making by pooling distributed information, yet systematically evaluating this capability has remained challenging. We introduce HiddenBench, a…

Computation and Language · Computer Science 2026-05-14 Yuxuan Li , Aoi Naito , Hirokazu Shirado

In continual RL we want agents capable of never-ending learning, and yet our evaluation methodologies do not reflect this. The standard practice in RL is to assume unfettered access to the deployment environment for the full lifetime of the…

Machine Learning · Computer Science 2025-08-11 Golnaz Mesbahi , Parham Mohammad Panahi , Olya Mastikhina , Steven Tang , Martha White , Adam White

The software powering today's vehicles surpasses mechatronics as the dominating engineering challenge due to its fast evolving and innovative nature. In addition, the software and system architecture for upcoming vehicles with automated…

Software Engineering · Computer Science 2017-06-13 Federico Giaimo , Christian Berger

Numerous software analysis tools exist today, yet applying them to diverse open-source projects remains challenging due to environment setup, dependency resolution, and tool configuration. LLM-based agents offer a potential solution, yet no…

Software Engineering · Computer Science 2026-04-20 Islem Bouzenia , Cristian Cadar , Michael Pradel

Automated program repair has traditionally focused on single-hunk defects, overlooking multi-hunk bugs that are prevalent in real-world systems. Repairing these bugs requires coordinated edits across multiple, disjoint code regions, posing…

Software Engineering · Computer Science 2025-11-17 Noor Nashid , Daniel Ding , Keheliya Gallaba , Ahmed E. Hassan , Ali Mesbah

Large Language Model (LLM) agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function…

Cryptography and Security · Computer Science 2025-07-10 Tarek Gasmi , Ramzi Guesmi , Ines Belhadj , Jihene Bennaceur

In the era of "Software Engineering 2.0" (SE 2.0), where intelligent agents collaborate with human engineers, Generative AI is advancing beyond code generation into Software Architecture (SA). While Large Language Models (LLMs) demonstrate…

Software Engineering · Computer Science 2026-03-10 Ha Vo , Nhut Tran , Khang Vo , Phat T. Tran-Truong , Son Ha

Large Language Model (LLM) agents can leverage multiple turns and tools to solve complex tasks, with prompt-based approaches achieving strong performance. This work demonstrates that Reinforcement Learning (RL) can push capabilities…

Computation and Language · Computer Science 2025-10-29 Vivek Kalyan , Martin Andrews

While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in…

Cryptography and Security · Computer Science 2026-03-25 Hyomin Lee , Sangwoo Park , Yumin Choi , Sohyun An , Seanie Lee , Sung Ju Hwang