17 papers
AtomSD: Procedural Atom-Guided Self-Distillation for LLM Agents
Bohan Yu, Pengfei Cao, Kai Tian +8
Large language models (LLMs) possess broad factual knowledge and strong reasoning capabilities, but solving complex tasks also requires procedural knowledge about how to act. Exist…
RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios
Chenhao Yuan, Bohan Yu, Yinhao Xu +10
Large language models (LLMs) increasingly tackle complex real-world tasks in specialized domains. However, identifying and correctly applying domain-specific rules remains challeng…
RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models
Bohan Yu, Shi-Yang Li, Pengfei Cao +2
Large language models (LLMs) are increasingly applied to specialized domains, where effective use of domain expertise often requires reasoning over complex rules in concrete scenar…
Emotion Understanding in Streaming Video with Trajectory-Aware Reliability
Qingsong Wang, Qigong Lei, Zitong Wang +6
Video emotion understanding is commonly studied as an offline classification problem, where the complete video segment is available before prediction. Real-time interaction, howeve…
Beyond Factual Knowledge: Benchmarking and Learning Step-Level Procedural Rule Reasoning in Large Language Models
Bohan Yu, Pengfei Cao, Chen Han +7
Large language models (LLMs) excel at text understanding and generation, yet still struggle to reliably understand and apply externally provided procedural rules at scale. To evalu…
Quantization Degradation in Large Language Models: A Signal-Noise Perspective
Chenxi Zhou, Pengfei Cao, Jinyu Ye +5
Post-training quantization reduces the deployment cost of large language models, yet how severely a quantized model degrades is not determined by bit-width alone. We systematically…
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Junlin Liu, Jiangwang Chen, Zixin Song +7
Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this with outcome-based reinforc…
PReM: Learning What to Preserve and When to Refresh for Context Compression
Bohan Yu, Lei Shen, Chenxi Zhou +5
Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds. However, existing comp…
STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios
Sirui Liang, Bohan Yu, Peiyu Wang +8
Large language models are increasingly used to power personal agents for everyday applications, but evaluating these agents remains a challenge. Existing benchmarks still rely on s…
TextShield-R1: Reinforced Reasoning for Tampered Text Detection
Chenfan Qu, Yiwu Zhong, Jian Liu +3
The growing prevalence of tampered images poses serious security threats, highlighting the urgent need for reliable detection methods. Multimodal large language models (MLLMs) demo…
Conformity Dynamics in LLM Multi-Agent Systems: The Roles of Topology and Self-Social Weighting
Chen Han, Jin Tan, Bohan Yu +2
Large Language Models (LLMs) are increasingly instantiated as interacting agents in multi-agent systems (MAS), where collective decisions emerge through social interaction rather t…
StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
Xinqi Jin, Hanxun Yu, Bohan Yu +8
Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is chall…
Active Perception Agent for Omnimodal Audio-Video Understanding
Keda Tao, Wenjie Du, Bohan Yu +3
Omnimodal large language models have made significant strides in unifying audio and visual modalities; however, they often face challenges in fine-grained cross-modal understanding…
SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention
Bohan Yu, Wei Huang, Kang Liu
This paper proposes SR-KI, a novel approach for integrating real-time and large-scale structured knowledge bases (KBs) into large language models (LLMs). SR-KI begins by encoding K…
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
Keda Tao, Kele Shao, Bohan Yu +3
Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding. However, the high computational cost of p…
EvolKV: Evolutionary KV Cache Compression for LLM Inference
Bohan Yu, Yekun Chai
Existing key-value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the…
TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering
Junnan Zhu, Jingyi Wang, Bohan Yu +4
LLMs have shown impressive progress in natural language processing. However, they still face significant challenges in TableQA, where real-world complexities such as diverse table…