English
Related papers

Related papers: Agentic Rubrics as Contextual Verifiers for SWE Ag…

200 papers

Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting…

AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no unified benchmark enables fair comparison across these approaches. We present Agentick, a…

Artificial Intelligence · Computer Science 2026-05-14 Roger Creus Castanyer , Pablo Samuel Castro , Glen Berseth

Agents based on large language models have recently shown strong potential on real-world software engineering (SWE) tasks that require long-horizon interaction with repository-scale codebases. However, most existing agents rely on…

Computation and Language · Computer Science 2025-12-29 Shukai Liu , Jian Yang , Bo Jiang , Yizhi Li , Jinyang Guo , Xianglong Liu , Bryan Dai

Automating real-world software engineering tasks remains challenging for large language model (LLM)-based agents due to the need for long-horizon reasoning over large, evolving codebases and making consistent decisions across interdependent…

Software Engineering · Computer Science 2026-04-14 Mahir Labib Dihan , Md Ashrafur Rahman Khan

Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like…

Software Engineering · Computer Science 2024-11-13 John Yang , Carlos E. Jimenez , Alexander Wettig , Kilian Lieret , Shunyu Yao , Karthik Narasimhan , Ofir Press

Agentic reinforcement learning increasingly relies on experience-driven scaling, yet real-world environments remain non-adaptive, limited in coverage, and difficult to scale. World models offer a potential way to improve learning efficiency…

Computation and Language · Computer Science 2026-03-06 Yixia Li , Hongru Wang , Jiahao Qiu , Zhenfei Yin , Dongdong Zhang , Cheng Qian , Zeping Li , Pony Ma , Guanhua Chen , Heng Ji

Current benchmarks for evaluating software engineering agents, such as SWE-Bench Verified, are predominantly derived from GitHub issues and fail to accurately reflect how developers interact with chat-based coding assistants in integrated…

Software Engineering · Computer Science 2026-01-27 Spandan Garg , Benjamin Steenhoek , Yufan Huang

Large language model agents have made strong progress on software engineering, yet current systems suffer from a context coupling problem: the standard code editing interface conflates code inspection, modification planning, and edit…

Software Engineering · Computer Science 2026-05-27 Yikai Zhang , Jiaxin Pei , Kenan Li , Qirui Jin , Maoquan Wang , Jin Pan , Yu Kang , Shengyu Fu , Elsie Nallipogu , Junjie Hu , Yufan Huang , Zijian Jin

Techniques for reliable rubric-based LLM evaluation -- ensemble judging, bias mitigation, few-shot calibration -- are scattered across papers with inconsistent terminology and partial implementations. We introduce Autorubric, an open-source…

Computation and Language · Computer Science 2026-04-07 Delip Rao , Chris Callison-Burch

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown…

Computation and Language · Computer Science 2025-02-27 Hao Peng , Yunjia Qi , Xiaozhi Wang , Zijun Yao , Bin Xu , Lei Hou , Juanzi Li

In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline,…

Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubric-based RL remains challenging: existing approaches often…

Computation and Language · Computer Science 2026-05-26 Xiaoyuan Li , Keqin Bao , Moxin Li , Yubo Ma , Yichang Zhang , Wenjie Wang , Fuli Feng , Dayiheng Liu

Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structure of the feedback signal: unstructured critique helps inconsistently across models, and…

Machine Learning · Computer Science 2026-05-19 Will LeVine , Brendan Evers , Sam Saltwick , Abhay Venkatesh

Explanations for AI models in high-stakes domains like medicine often lack verifiability, which can hinder trust. To address this, we propose an interactive agent that produces explanations through an auditable sequence of actions. The…

Artificial Intelligence · Computer Science 2025-11-04 Yuhang Huang , Zekai Lin , Fan Zhong , Lei Liu

Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering. However, they often struggle to maintain consistent performance across…

Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs). However, existing benchmarks for code agent evaluation face two major limitations. First, creating…

Software Engineering · Computer Science 2026-03-24 Lingyue Fu , Bolun Zhang , Hao Guan , Yaoming Zhu , Lin Qiu , Weiwen Liu , Xuezhi Cao , Xunliang Cai , Weinan Zhang , Yong Yu

Verifying LLM-generated systems code is hard: bugs are prevalent, formal specifications are missing, and safety contracts are encoded implicitly at call sites rather than enforced at function boundaries. We propose agentic model checking, a…

Software Engineering · Computer Science 2026-05-21 Youcheng Sun , Jiawen Liu , Daniel Kroening , Jason Xue

Code Search is a key task that many programmers often have to perform while developing solutions to problems. Current methodologies suffer from an inability to perform accurately on prompts that contain some ambiguity or ones that require…

Software Engineering · Computer Science 2024-08-22 Sarthak Jain , Aditya Dora , Ka Seng Sam , Prabhat Singh

Agent-based program repair offers to automatically resolve complex bugs end-to-end by combining the planning, tool use, and code generation abilities of modern LLMs. Recent work has explored the use of agent-based repair approaches on the…

Software Engineering · Computer Science 2025-01-14 Pat Rondon , Renyao Wei , José Cambronero , Jürgen Cito , Aaron Sun , Siddhant Sanyam , Michele Tufano , Satish Chandra

As agentic AI systems increasingly operate autonomously, establishing trust through verifiable evaluation becomes critical. Yet existing benchmarks lack the transparency and auditability needed to assess whether agents behave reliably. We…

Computation and Language · Computer Science 2025-12-02 Hyunjun Kim , Sooyoung Ryu
‹ Prev 1 3 4 5 6 7 10 Next ›