Junqi Xiong
3 papers · 2026–2026 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Top co-authors
Research topics
Keywords
software engineering
(1)
vision-language model
(1)
large language model
(1)
web development
(1)
agentic coding
(1)
benchmark
(1)
trajectory
(1)
instruction
(1)
vision
(1)
interaction
(1)
implementation
(1)
skills
(1)
github pull requests
(1)
real-world developer workflows
(1)
self-evolving
(1)
guide
(1)
root-cause feedback
(1)
multimodal code agents
(1)
Papers
MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
EMNLP 2026
SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
ICML 2026
WebCompass: Evaluating Multimodal Code Agents in Web Development from Vision, Instruction, and Interaction to Implementation
EMNLP 2026