Dan Hao

T RACE : Evaluating Execution Efficiency of LLM-Based Code Translation

LAMDA: Leveraging Large Language Models for Better API Misuse Detection via Multi-Agent Collaboration

Modern software development heavily relies on reusing third-party and internal Application Programming Interfaces (APIs). However, API misuses occur frequently, leading to program crashes, security vulnerabilities, and other unexpected behaviors. To detect API misuse, many existing approaches mine API usage patterns fr...

MOCA: A Hierarchical Semantic-Enhanced Code Edit Framework for Multilingual Code Co-Evolution

Multilingual code co-evolution aims to propagate code edits across programming languages while preserving functional consistency, yet the task remains challenging in real-world repositories. Our motivating examples reveal two key challenges: (1) Existing models fail to infer the rationale behind source edits and may om...

Decomposing Ponzi Schemes: Multi-aspect Lifecycle Analysis for Detecting Fraudulent Smart Contracts

Smart contracts have enabled decentralized financial applications, enabling trustless and transparent asset management. However, their programmability also expands the attack surface, allowing adversaries to encode fraudulent economic behaviors directly into contract logic. Among these threats, Smart Contract Ponzi Sch...

From Greedy Steps to Global Optimization: Learning Sequential Test Suite Generation

With the rapid evolution of Large Language Models (LLMs), automated software testing is witnessing a paradigm shift. While proprietary models like GPT-4o demonstrate impressive capabilities, their high deployment costs and data privacy concerns make open-source LLMs the practical imperative for many academic and indust...

Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents

Latent Observations, Hard Actions (LOHA), a context layout that separates compressed history from text needed for exact reference, with Anchored Context Distillation (ACD), a training method that enables latent reading while constraining behavioral drift are combined to reduce context while preserving action-critical i...

WarmTuner: Program-Specific Warm Starts for Compiler Autotuning via Offline-to-Online Reinforcement Learning

WarmTuner is an offline-to-online reinforcement learning framework that turns historical records into a program-conditioned policy that predicts each flag's setting over the full flag space and remains adaptable on the target program and significantly outperforming the compared techniques.

CausalRepair: Bridging the Causality Gap in Large Language Model-Based Automated Program Repair via Dual-Slicing

CausalRepair is proposed, a conversation-driven APR framework based on minimal causal context, i.e., the essential dependencies required to explain a failure, outperforming state-of-the-art approaches such as ReinFix and TSAPR, while reducing the average repair cost to $0.029 per bug.

PurifAI: Detecting and Fixing Search-Induced Distortions in Web-Augmented LLMs

PurifAI, a proactive, model-agnostic, cache-level purification system designed for safety- and compliance-sensitive deployments, is presented, explicitly designed to preserve knowledge alignment with a pre-defined trusted knowledge core.