collaborators

7 papers

cs.AI2026

SkillEval: Decomposing Agent Skill Quality into Interpretable Signals

Jiahui Han, Qinuo Li, Ziheng Peng +6

Agent skills provide reusable procedural knowledge that helps agents solve specialized tasks. As their use expands, evaluating skill quality becomes increasingly important. Existin…

cs.CL2026

Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?

Yubo Gao, Haotian Wu, Xiaoyu Xu +9

Existing methods for multimodal sentiment analysis (MSA) under missing modalities usually follow a repair-first paradigm. We revisit this assumption and ask: \emph{should every mis…

cs.AI2026

Interactive Learning for LLM Reasoning

Hehai Lin, Shilei Cao, Sudong Wang +5

Existing multi-agent learning approaches have developed interactive training environments to explicitly promote collaboration among multiple Large Language Models (LLMs), thereby c…

cs.CL2026

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs

Yubo Gao, Haotian Wu, Hong Chen +8

Chain-of-Thought (CoT) has significantly enhanced LLM reasoning, yet often incurs substantial computational overhead due to "overthinking": generating excessively long rationales w…

cs.CL2026

FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline

Haotian Wu, Shufan Jiang, Chios Chen +5

As large language models (LLMs) advance in role-playing (RP) tasks, existing benchmarks quickly become obsolete due to their narrow scope, outdated interaction paradigms, and limit…

cs.CL2025

EffiReason-Bench: A Unified Benchmark for Evaluating and Advancing Efficient Reasoning in Large Language Models

Junquan Huang, Haotian Wu, Yubo Gao +7

Large language models (LLMs) with Chain-of-Thought (CoT) prompting achieve strong reasoning but often produce unnecessarily long explanations, increasing cost and sometimes reducin…