English
Related papers

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

200 papers

Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineering approaches primarily rely on the context generated from the past experience and retrieval…

Artificial Intelligence · Computer Science 2026-04-10 Linbo Liu , Guande Wu , Han Ding , Yawei Wang , Qiang Zhou , Yuzhe Lu , Zhichao Xu , Huan Song , Panpan Xu , Lin Lee Cheong

Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41\% of total evaluation time) and imbalanced task horizon and difficulty distributions that make aggregate scores unreliable. To…

Artificial Intelligence · Computer Science 2026-04-13 Wang Yang , Chaoda Song , Xinpeng Li , Debargha Ganguly , Chuang Ma , Shouren Wang , Zhihao Dou , Yuli Zhou , Vipin Chaudhary , Xiaotian Han

The capabilities of AI-assisted coding are progressing at breakneck speed. Chat-based vibe coding has evolved into fully fledged AI-assisted, agentic software development using agent scaffolds where the human developer creates a plan that…

Software Engineering · Computer Science 2026-04-24 Magnus Palmblad , Jared M. Ragland , Benjamin A. Neely

Benchmarks for Software Engineering (SE) AI agents, most notably SWE-bench, have catalyzed progress in programming capabilities of AI agents. However, they overlook critical developer workflows such as Version Control System (VCS)…

Software Engineering · Computer Science 2025-05-29 Tobias Lindenbauer , Egor Bogomolov , Yaroslav Zharov

As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, understanding which tasks will challenge agents and why becomes increasingly difficult. This is…

Artificial Intelligence · Computer Science 2026-04-02 Chris Ge , Daria Kryvosheieva , Daniel Fried , Uzay Girit , Kaivalya Hariharan

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…

Artificial Intelligence · Computer Science 2026-04-08 Hangoo Kang , Tarun Suresh , Jon Saad-Falcon , Azalia Mirhoseini

Evaluating LLM agent trajectories is fundamentally task-specific: a code-debugging agent should be judged on Correctness and Error Handling, not on Fluency or Safety. Yet the dominant paradigm -- LLM-as-Judge with a fixed rubric -- applies…

Artificial Intelligence · Computer Science 2026-05-12 Liang Ding

Agentic Software Engineering (SE 3.0) represents a new era where intelligent agents are tasked not with simple code generation, but with achieving complex, goal-oriented SE objectives. To harness these new capabilities while ensuring…

Software Engineering · Computer Science 2025-09-24 Ahmed E. Hassan , Hao Li , Dayi Lin , Bram Adams , Tse-Hsun Chen , Yutaro Kashiwa , Dong Qiu

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

Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored. We introduce…

Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such…

Computation and Language · Computer Science 2026-04-13 Manan Suri , Xiangci Li , Mehdi Shojaie , Songyang Han , Chao-Chun Hsu , Shweta Garg , Aniket Anand Deshmukh , Varun Kumar

AI coding agents can resolve real-world software issues, yet they frequently introduce regressions -- breaking tests that previously passed. Current benchmarks focus almost exclusively on resolution rate, leaving regression behavior…

Software Engineering · Computer Science 2026-03-20 Pepe Alonso , Sergio Yovine , Victor A. Braberman

Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To…

Cryptography and Security · Computer Science 2026-05-19 Xianzhen Luo , Jingyuan Zhang , Shiqi Zhou , Rain Huang , Chuan Xiao , Qingfu Zhu , Zhiyuan Ma , Xing Yue , Yang Yue , Wencong Zeng , Wanxiang Che

With the advancement of Agentic AI, researchers are increasingly leveraging autonomous agents to address challenges in software engineering (SE). However, the large language models (LLMs) that underpin these agents often function as black…

Software Engineering · Computer Science 2026-04-03 Jingyue Li , André Storhaug

The delivery of traditional substance education has remained problematic due to challenges in scalability, personalization, and the currency of information in a rapidly evolving substance use landscape. While artificial intelligence (AI)…

Computation and Language · Computer Science 2026-05-04 Kosar Haghani , Zahra Kolagar , Mohammed Atiquzzaman

Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…

Systematic literature reviews are essential for synthesizing scientific evidence but are costly, difficult to scale and time-intensive, creating bottlenecks for evidence-based policy. We study whether large language models can automate the…

Executable software engineering data is valuable for training SWE agents, but scaling it remains difficult for two reasons: only a small fraction of real repository changes yield verifiable, high-signal task instances, and naively building…

Software Engineering · Computer Science 2026-03-24 Jiarong Liang , Zhiheng Lyu , Zijie Liu , Xiangchao Chen , Ping Nie , Kai Zou , Wenhu Chen

Large language models (LLMs) often achieve high performance in native language identification (NLI) benchmarks by leveraging superficial contextual clues such as names, locations, and cultural stereotypes, rather than the underlying…

Computation and Language · Computer Science 2025-09-23 Ahmet Yavuz Uluslu , Tannon Kew , Tilia Ellendorff , Gerold Schneider , Rico Sennrich

The performance of Large Language Models (LLMs) is highly sensitive to the prompts they are given. Drawing inspiration from the field of prompt optimization, this study investigates the potential for enhancing Automated Essay Scoring (AES)…

Computation and Language · Computer Science 2025-10-13 Keno Harada , Lui Yoshida , Takeshi Kojima , Yusuke Iwasawa , Yutaka Matsuo