中文
相关论文

相关论文: TrajAudit: Automated Failure Diagnosis for Agentic…

200 篇论文

Software vulnerability detection is critical in software en- gineering as security flaws arise from complex interactions across code structure, repository context, and runtime conditions. Existing meth- ods are limited by local code views,…

软件工程 · 计算机科学 2026-03-17 Renwei Meng , Haoyi Wu , Jingming Wang , Haoyan Bai

From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search…

计算与语言 · 计算机科学 2025-08-29 Ryan Wong , Jiawei Wang , Junjie Zhao , Li Chen , Yan Gao , Long Zhang , Xuan Zhou , Zuo Wang , Kai Xiang , Ge Zhang , Wenhao Huang , Yang Wang , Ke Wang

Large Language Models (LLMs) are increasingly deployed as autonomous agents that reason, use tools, and act over multiple steps. Yet most hallucination benchmarks still evaluate only the final output, missing failures that originate in…

Recent advances in reasoning models and agentic AI systems have led to an increased reliance on diverse external information. However, this shift introduces input contexts that are inherently noisy, a reality that current sanitized…

人工智能 · 计算机科学 2026-01-13 Seongyun Lee , Yongrae Jo , Minju Seo , Moontae Lee , Minjoon Seo

Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this…

Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation…

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…

软件工程 · 计算机科学 2026-04-20 Islem Bouzenia , Cristian Cadar , Michael Pradel

Tool using agents often fail for operational reasons even when language understanding is strong. Common causes include invalid arguments, interface drift, weak recovery, and inefficient retry behavior. We introduce ToolMisuseBench, an…

软件工程 · 计算机科学 2026-04-03 Akshey Sigdel , Rista Baral

Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code remains underexplored. Due to the size and complexities of systems code, making changes to a systems…

Large language models (LLMs) have shown impressive capability to understand and develop code. However, their capability to rigorously reason about and prove code correctness remains in question. This paper offers a comprehensive study of…

操作系统 · 计算机科学 2026-04-16 Chenyuan Yang , Natalie Neamtu , Chris Hawblitzel , Jacob R. Lorch , Shan Lu

Large language models are increasingly being assembled into medical multi-agent systems that emulate multidisciplinary consultation through specialist roles, peer review and consensus formation. In clinical decision support, however,…

LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial task design, high-capacity model generation, and manual filtering. Despite the high cost of…

密码学与安全 · 计算机科学 2026-05-05 Wenlong Meng , Chen Gong , Terry Yue Zhuo , Fan Zhang , Kecen Li , Zheng Liu , Zhou Yang , Chengkun Wei , Wenzhi Chen

Large Language Models have demonstrated profound utility in the medical domain. However, their application to autonomous Electronic Health Records~(EHRs) navigation remains constrained by a reliance on curated inputs and simplified…

计算与语言 · 计算机科学 2026-01-21 Yusheng Liao , Chuan Xuan , Yutong Cai , Lina Yang , Zhe Chen , Yanfeng Wang , Yu Wang

Automated Program Repair (APR) struggles with complex logic errors and silent failures. Current LLM-based APR methods are mostly static, relying on source code and basic test outputs, which fail to accurately capture complex runtime…

软件工程 · 计算机科学 2026-04-06 Jiaqing Wu , Tong Wu , Manqing Zhang , Yunwei Dong , Bo Shen

Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning tracking who speaks, maintaining roles, and…

Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…

人工智能 · 计算机科学 2026-01-26 Donghao Huang , Gauri Malwe , Zhaoxia Wang

With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to…

人工智能 · 计算机科学 2025-09-19 NVJK Kartik , Garvit Sapra , Rishav Hada , Nikhil Pareek

Bug localization remains a key bottleneck in downstream software maintenance tasks, including root cause analysis, triage, and automated program repair (APR), despite recent advances in large language model (LLM)-based repair systems.…

软件工程 · 计算机科学 2026-05-19 Md Afif Al Mamun , Gias Uddin

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…

计算与语言 · 计算机科学 2025-12-02 Hyunjun Kim , Sooyoung Ryu

Scientific discovery is often slowed by the manual development of computational tools needed to analyze complex experimental data. Building such tools is costly and time-consuming because scientists must iteratively review literature, test…

人工智能 · 计算机科学 2026-05-19 Alistair Turcan , Kexin Huang , Lei Li , Martin Jinye Zhang