1 citations · 1 across the 14 of their papers we have counts for
14 papers
Trajectory-Aware Benchmark Subset Selection for Cost-Efficient Software Engineering Agent Regression Testing
Mahmoud Ayyad, Zehao Wang, Jiho Shin +2
Autonomous software engineering agents (SWE-agents) automate coding tasks. Each agent update may require re-running the full benchmark to detect regressions and improvements, at a…
Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework
Chenglin Li, Yisen Xu, Zehao Wang +3
Autonomous coding agents powered by large language models can now generate code patches directly from bug reports, but a fundamental gap remains: once a patch is produced, no mecha…
Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection
Sihan Hou, Xinmeng Hou, Zhijun Zhang +5
Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external observations manipulate subsequ…
Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents
Zehao Wang, Yisen Xu, Chenglin Li +5
Long-horizon coding agents accumulate hundreds of actions and observations in their trajectories, yet nothing in this record indicates which observations still describe the reposit…
Preventing Premature Commitment in Coding Agents with an Evidence-Conditioned Execution Layer
Yisen Xu, Chenglin Li, Zehao Wang +2
LLM-based coding agents often edit source code or submit patches before examining enough repository evidence to justify the change, a failure pattern we call premature commitment.…
Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory
Suozhao Ji, Baodong Wu, Zehao Wang +8
Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions. Existing memory systems often store observations as isolate…
FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation
Zehao Wang, Guanglei Yang, Yihan Zeng +4
Federated fine-tuning of foundation models with Low-Rank Adaptation (LoRA) provides an efficient solution for reducing communication and computation costs while preserving data loc…
AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution
Zehao Wang, Yihan Zeng, Zidong Gong +5
Post-training via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is crucial for enhancing reasoning in Multimodal Large Language Models (MLLMs), yet existing paradigm…
Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild
Zhimin Zhao, Zehao Wang, Abdul Ali Bangash +2
Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result reporting. Despite their crit…
When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems
Zehao Wang, Shilong Jin, Zhao Cao +1
LLM-based multi-agent systems can fail even when planned actions are executed correctly because agents may misjudge their knowledge when evaluating plan feasibility, a phenomenon w…
Probe to Generate: Program Variant-Guided Test Augmentation for Repository-Level Repair Benchmarks
Chenglin Li, Yisen Xu, Zehao Wang +3
Test-based benchmarks such as SWE-bench have become a standard basis for evaluating automated issue resolution agents, deeming a patch correct if it passes a provided regression te…
From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair
Chenglin Li, Yisen Xu, Zehao Wang +3
Repository-level automated program repair (APR) requires long-horizon reasoning over interdependent decisions. However, most LLM-based approaches reconstruct repair reasoning indep…
A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models
Yixi Wu, Pengfei He, Zehao Wang +3
Large language models (LLMs) like GitHub Copilot and ChatGPT have emerged as powerful tools for code generation, significantly enhancing productivity and accelerating software deve…
Identifying Performance-Sensitive Configurations in Software Systems through Code Analysis with LLM Agents
Zehao Wang, Dong Jae Kim, Tse-Hsun Chen
Configuration settings are essential for tailoring software behavior to meet specific performance requirements. However, incorrect configurations are widespread, and identifying th…