Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Peng Chen

Peng Chen

14 indexed papers

Recent (6 mo)
13
With code
0
Influential cites
0
Benchmarked
0

Publications per year

14
26

Top categories

AI×9Crypto×4Software Eng.×3NLP×3Distributed×1ML×1Vision×1Numerical Analysis×1

Frequent co-authors

Chen Zhao3×
Danqing Huang3×
Yunlong Lyu2×
Hao Chen2×
Leo Luo2×
Haining Xie2×

Research Timeline

2026
FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing

FuzzAgent introduces a multi-agent, evolutionary system that significantly improves library fuzzing by iteratively refining the test suite based on runtime feedback, achieving superior coverage and bug detection compared to state-of-the-art methods.

Privacy-Preserving Screening for Record Linkage

The paper introduces Appraisal, a novel Screening-then-Linkage framework (PPRS) that significantly improves the scalability and efficiency of Privacy-Preserving Record Linkage by incorporating a lightweight screening phase.

EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

The paper proposes Preference Delta Aggregation (PDA), a framework that aggregates multiple weak preference signals derived from smaller model pairs using LoRA merging to significantly boost the performance of a strong large language model.

From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

The paper proposes Preference Delta Aggregation (PDA), a framework that aggregates multiple weak preference signals derived from smaller model pairs using LoRA merging to significantly boost the performance of a strong large language model.

SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex benchmarks.

SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex benchmarks.

DIG: Oracle-Guided Directed Input Generation for One-Day Vulnerabilities

A new approach to generating proof-of-concept inputs for one-day vulnerabilities using a language model and an oracle.

Error-Conditioned Neural Solvers

This paper proposes Error-conditioned Neural Solvers (ENS) for neural surrogate models to iteratively correct predictions by using the PDE residual field as input, achieving higher accuracy than optimization-based methods.

Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities

The paper introduces DataGovBench, a benchmark for evaluating Large Language Models in real-world data analysis scenarios, revealing significant performance gaps with state-of-the-art models.

Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework

Aries is a full-stack experimentation framework for autonomous agents that separates task semantics from execution configurations, reconstructs agent trajectories, and exposes stateful tool execution.

Last Secure Code Benchmark: Is the Code You Vibe Secure?

The paper introduces the Last Secure Code Benchmark to evaluate secure code generation by coding agents.

Efficient Program Reduction for Library Fuzzing Harnesses

HarnessMinimizer is a system for efficiently minimizing C/C++ library fuzzing harnesses to simplify crash investigation.

Highlighted terms show continued research focus across papers

Papers

cs.SEEmpiricalRecentOct 16, 2026

Efficient Program Reduction for Library Fuzzing Harnesses

Haiying Li, Yunlong Lyu, Peng Chen, Hao Chen

HarnessMinimizer is a system for efficiently minimizing C/C++ library fuzzing harnesses to simplify crash investigation.

View →
cs.CRcs.AIEmpiricalRecent
Oct 10, 2026

Last Secure Code Benchmark: Is the Code You Vibe Secure?

Tianyi Wu, Chao Ge, Peng Chen, Fengji Zhang +11 more

The paper introduces the Last Secure Code Benchmark to evaluate secure code generation by coding agents.

View →
cs.DCEmpiricalRecentJul 31, 2026

Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework

Leonid Kondrashov, Hongrui Liu, JooYoung Park, Boxi Zhou +13 more

Aries is a full-stack experimentation framework for autonomous agents that separates task semantics from execution configurations, reconstructs agent trajectories, and exposes stateful tool execution.

View →
cs.CLcs.AIEmpiricalRecentJul 7, 2026

Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities

So Hasegawa, Shailaja Keyur Sampat, Lei Liu, Wei-Peng Chen

The paper introduces DataGovBench, a benchmark for evaluating Large Language Models in real-world data analysis scenarios, revealing significant performance gaps with state-of-the-art models.

View →
cs.LGcs.AIcs.CVEmpiricalRecentJun 25, 2026

Error-Conditioned Neural Solvers

Haina Jiang, Liam Wang, Peng-Chen Chen, Min Seop Kwak +3 more

This paper proposes Error-conditioned Neural Solvers (ENS) for neural surrogate models to iteratively correct predictions by using the PDE residual field as input, achieving higher accuracy than optim…

View →
cs.CRcs.SEEmpiricalRecentJun 11, 2026

DIG: Oracle-Guided Directed Input Generation for One-Day Vulnerabilities

Andrew Bao, Haochen Zeng, Peng Chen, Stephen McCamant +1 more

A new approach to generating proof-of-concept inputs for one-day vulnerabilities using a language model and an oracle.

View →
cs.AIRecentMay 31, 2026

SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback

Leo Luo, Haining Xie, Siqi Shen, Zhipeng Ma +7 more

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex be…

View →
cs.AIRecentMay 31, 2026

SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback

Leo Luo, Haining Xie, Siqi Shen, Zhipeng Ma +7 more

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex be…

View →
cs.AIRecentMay 29, 2026

From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

Qi Sun, Siyue Zhang, Yulin Chen, Yuxiang Xue +2 more

The paper proposes Preference Delta Aggregation (PDA), a framework that aggregates multiple weak preference signals derived from smaller model pairs using LoRA merging to significantly boost the perfo…

View →
cs.AIRecentMay 29, 2026

From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

Qi Sun, Siyue Zhang, Yulin Chen, Yuxiang Xue +2 more

The paper proposes Preference Delta Aggregation (PDA), a framework that aggregates multiple weak preference signals derived from smaller model pairs using LoRA merging to significantly boost the perfo…

View →
cs.CLcs.AIRecentMay 28, 2026

EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL

Huawei Zheng, Sen Yang, Zhaorui Yang, Yuhui Zhang +11 more

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

View →
cs.CLcs.AIRecentMay 28, 2026

EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL

Huawei Zheng, Sen Yang, Zhaorui Yang, Yuhui Zhang +11 more

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

View →
cs.CRRecentMay 26, 2026

Privacy-Preserving Screening for Record Linkage

Chenyu Huang, Fan Zhang, Huangxun Chen, Yongjun Zhao +3 more

The paper introduces Appraisal, a novel Screening-then-Linkage framework (PPRS) that significantly improves the scalability and efficiency of Privacy-Preserving Record Linkage by incorporating a light…

View →
cs.SEcs.CRMay 14, 2026

FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing

Yunlong Lyu, Peng Chen, Fengyi Wu, Junzhe Yu +2 more

FuzzAgent introduces a multi-agent, evolutionary system that significantly improves library fuzzing by iteratively refining the test suite based on runtime feedback, achieving superior coverage and bu…

View →