English
Related papers

Related papers: A Judge Agent Closes the Reliability Gap in AI-Gen…

200 papers

Autonomous science agents built on large language models (LLMs) are increasingly used to generate hypotheses, design experiments, and produce reports. However, prior work mainly targets open-ended scientific problems with subjective outputs…

Computation and Language · Computer Science 2026-03-24 Tianshu Zhang , Huan Sun

Autonomous agents utilizing Large Language Models (LLMs) have demonstrated remarkable capabilities in isolated medical tasks like diagnosis and image analysis, but struggle with integrated clinical workflows that connect diagnostic…

Artificial Intelligence · Computer Science 2025-10-14 Hongjie Zheng , Zesheng Shi , Ping Yi

Mathematical modeling is a cornerstone of scientific discovery and engineering practice, enabling the translation of real-world problems into formal systems across domains such as physics, biology, and economics. Unlike mathematical…

Artificial Intelligence · Computer Science 2025-05-21 Fan Liu , Zherui Yang , Cancheng Liu , Tianrui Song , Xiaofeng Gao , Hao Liu

As automated reasoning systems advance rapidly, there is a growing need for research-level formal mathematical problems to accurately evaluate their capabilities. To address this, we present Formal Conjectures, an evolving benchmark of…

Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we call agentic code reasoning, and introduce semi-formal reasoning: a structured prompting methodology that…

Software Engineering · Computer Science 2026-03-05 Shubham Ugare , Satish Chandra

Miscalibrated confidence scores are a practical obstacle to deploying AI in clinical settings. A model that is always overconfident offers no useful signal for deferral. We present a multi-agent framework that combines domain-specific…

Artificial Intelligence · Computer Science 2026-03-26 John Ray B. Martinez

Recently, using Large Language Models (LLMs) to generate optimization models from natural language descriptions has became increasingly popular. However, a major open question is how to validate that the generated models are correct and…

Artificial Intelligence · Computer Science 2026-04-07 Alexander Zadorojniy , Segev Wasserkrug , Eitan Farchi

As large language models (LLMs) are increasingly considered for automated assessment and feedback, understanding when LLM marking can be trusted is essential. We evaluate LLM-as-a-judge marking across three physics assessment formats -…

Physics Education · Physics 2026-03-17 Will Yeadon , Tom Hardy , Paul Mackay , Elise Agra

This manuscript signals a new era in the integration of artificial intelligence with software engineering, placing machines at the pinnacle of coding capability. We present a formalized, iterative methodology proving that AI can fully…

Software Engineering · Computer Science 2024-12-09 Alex , Liu , Vivian , Chi

AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation…

Artificial Intelligence · Computer Science 2026-02-24 Stephan Rabanser , Sayash Kapoor , Peter Kirgis , Kangheng Liu , Saiteja Utpala , Arvind Narayanan

Evaluation is no longer a final checkpoint in the machine learning lifecycle. As AI systems evolve from static models to compound, tool-using agents, evaluation becomes a core control function. The question is no longer "How good is the…

Computation and Language · Computer Science 2026-02-23 Ali El Filali , Inès Bedar

We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper's repository, we…

Artificial Intelligence · Computer Science 2026-03-13 Aniketh Garikaparthi , Manasi Patwardhan , Arman Cohan

Software testing is a crucial phase in the software development lifecycle (SDLC), ensuring that products meet necessary functional, performance, and quality benchmarks before release. Despite advancements in automation, traditional methods…

Software Engineering · Computer Science 2026-03-10 Mohammad Baqar , Rajat Khanda

Evaluating the correctness of code generated by AI is a challenging open problem. In this paper, we propose a fully automated method, named ACCA, to evaluate the correctness of AI-generated code for security purposes. The method uses…

Software Engineering · Computer Science 2024-06-11 Domenico Cotroneo , Alessio Foggia , Cristina Improta , Pietro Liguori , Roberto Natella

The advancement of Artificial Intelligence (AI) has created opportunities for e-learning, particularly in automated assessment systems that reduce educators' workload and provide timely feedback to students. However, developing effective…

Computers and Society · Computer Science 2025-02-11 Long Zhang , Meng Zhang , Wei Lin Wang , Yu Luo

Large language models are moving scientific research from text assistance toward agentic workflows, yet biological research requires strong object validation, methodological suitability, reproducibility, and auditability. Prompt…

Quantitative Methods · Quantitative Biology 2026-05-25 Zhenyu Ma , Yuyang Song , Chunyi Yang , Jingyi Zhu , Limei Xu , Min Xiao , Xukai Jiang

The convergence of LLM-powered research assistants and AI-based peer review systems creates a critical vulnerability: fully automated publication loops where AI-generated research is evaluated by AI reviewers without human oversight. We…

Cryptography and Security · Computer Science 2025-10-22 Fengqing Jiang , Yichen Feng , Yuetai Li , Luyao Niu , Basel Alomair , Radha Poovendran

Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze datasets and produce answers to statistical questions. However, these systems can reach…

Artificial Intelligence · Computer Science 2026-04-14 Zachary T. Rewolinski , Austin V. Zane , Hao Huang , Chandan Singh , Chenglong Wang , Jianfeng Gao , Bin Yu

AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product decisions that are invisible in the source code alone. We introduce a controlled benchmark…

Software Engineering · Computer Science 2026-05-12 Drew Dillon , Kasyap Varanasi

Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities extend to program verification, we evaluate Claude Code in an agentic proving…

Artificial Intelligence · Computer Science 2026-05-25 Alessandro Sosso , Akhil Arora , Bas Spitters