activity
20242026
collaborators

10 papers

cs.PL2026

ETAS: An Effect-Typed Language for Agent Systems

Huiri Tan, Yikun Wang, Puyang Zhang +2

ETAS is a programming language for agent systems that treats model-backed agents, tool calls, prompts, typed memory, human approvals, policies, and execution traces as semantic pro…

cs.SE2026

Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports

Jingyi Chen, Songqiang Chen, Hengcheng Zhu +3

LLM agents span command-line interfaces (e.g., Codex) and agent frameworks (e.g., LangChain), integrating backend LLMs with harness code that parses model outputs, controls agent l…

cs.CL2026

WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning

Juyong Jiang, Chenglin Cai, Chansung Park +4

While Large Language Models (LLMs) excel at function-level code generation, project-level tasks such as generating functional and visually aesthetic multi-page websites remain high…

cs.SE2026

CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora

Shangyu Li, Juyong Jiang, Meibo Ren +7

Transpilation, or code translation, aims to convert source code from one programming language (PL) to another. It is beneficial for many downstream applications, from modernizing l…

cs.CL2026

ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

Juyong Jiang, Jiasi Shen, Sunghun Kim +3

While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward pass often hit a performance ce…

cs.CL2026

TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models

Chansung Park, Juyong Jiang, Fan Wang +4

Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challen…