12 papers
Do Coding Agents Understand Why Systems Crash---and Why They Don't?
Chenxi Huang, Haonan Wang, Jinghe Zhang +7
Coding agents are increasingly capable of fixing real-world bugs, yet they still struggle with large systems codebases such as the Linux kernel. To understand why, we test how agen…
Probe-and-Resume: When and How to Evaluate Agent Execution
Jiakai Xu, Tiancheng Ge, Tujie Guan +4
Test-time search can improve agent performance by exploring alternative actions and using a critic to select promising branches. We study this approach in terminal-based computer-u…
StateFork: Branchable Infrastructure for Agent Exploration
Jiakai Xu, Tianle Zhou, Georgios Liargkovas +5
AI agents improve task success by exploring multiple trajectories, but for computer-use agents each trajectory modifies external environment state. Branching from an intermediate p…
Passes Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development
Haocheng Xia, Eugene Wu, Yongjoo Park
Parallel coding agents can produce patches that work alone but fail when merged. This happens when one agent changes an interface or rule that another agent still relies on. We stu…
Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety
Charlie Summers, Prajwal Raghunath, Aaditya Pai +4
LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/outputs, or rely on LLM judges;…
FlowCheck: Helping End-Users Specify and Verify Intent in Vibe-Coded Web Apps
Reya Vir, Lydia Chilton, Zhuo Zhang +1
Vibe-coded applications often contain silent behavioral failures in which the interface appears functional even though user-visible information does not flow to the expected state…
SANA: What Matters for QA Agents over Massive Data Lakes?
Austin Senna Wijaya, Jiaxiang Liu, Haonan Wang +1
Exploratory question answering (EQA) over data lakes requires an LLM agent to discover relevant sources, analyze retrieved data, and adapt its actions based on intermediate results…
LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake
Haonan Wang, Jiaxiang Liu, Yurong Liu +11
Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved. In cont…
Data Flow Control: Data Safety Policies for AI Agents
Charlie Summers, Eugene Wu
Agents increasingly generate SQL, orchestrate pipelines, and automate data analysis on behalf of users. While recent work improves query correctness, correctness is not safety. A q…
BranchBench: Aligning Database Branching with Agentic Demands
Elaine Ang, Sam Weldon, In Keun Kim +3
Branchable databases are evolving from developer tools to infrastructure for agentic workloads characterized by speculative mutations and non-linear state exploration. Traditional…
Toward Systems Foundations for Agentic Exploration
Jiakai Xu, Tianle Zhou, Eugene Wu +1
Agentic exploration, letting LLM-powered agents branch, backtrack, and search across many execution paths, demands systems support well beyond today's pass-at-k resets. Our benchma…
An approach for systematic decomposition of complex llm tasks
Tianle Zhou, Jiakai Xu, Guanhong Liu +3
Large Language Models (LLMs) suffer from reliability issues on complex tasks, as existing decomposition methods are heuristic and rely on agent or manual decomposition. This work i…