Fangwen Mu
3 papers · 2022–2026 · 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.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
Top co-authors
Research topics
Keywords
intent classification
(1)
text-to-image model
(1)
evolutionary algorithm
(1)
multimodal language model
(1)
mutual learning
(1)
execution trace
(1)
dialogue disentanglement
(1)
failure diagnosis
(1)
differential evolution
(1)
large language model
(1)
multi-agent system
(1)
prompt template
(1)
chat slice
(1)
template stealing
(1)
failure attribution
(1)
Papers
Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems
ACL 2026
Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach
ACL 2025
MuiDial: Improving Dialogue Disentanglement with Intent-Based Mutual Learning
IJCAI 2022