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(LLMs) advance in role-playing (RP) tasks, existing benchmarks quickly become obsolete due to their narrow scope, outdated interaction paradigms, and limit…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