9 papers
Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization
Jiawei Kong, Hao Fang, Shunxiang Liao +5
Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallu…
Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation
Zhengda Jin, Bingbing Wang, Jing Li +2
Long-term memory is essential for persistent LLM agents, yet prevailing architectures store historical interactions as unstructured, flat text. This unconstrained storage induces p…
CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents
Yihong Tang, Kehai Chen, Liang Yue +2
Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language…
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
Ruotao Xu, Yixin Ji, Yu Luo +5
Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of the underlying language mod…
SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
Weiyang Huang, Xuefeng Bai, Kehai Chen +4
Large Reasoning Models (LRMs) have revolutionized complex problem-solving, yet they exhibit a pervasive "overthinking", generating unnecessarily long reasoning chains. While curren…
Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
Quantong Qiu, Zhiyi Hong, Yi Yang +5
The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanis…