9 papers
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Ang Li, Ben Liu, Bin Han +215
Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve,…
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Xiaochong Lan, Pu Ning, Quan Chen +8
Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inhe…
Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation
Qi Cao, Jian Lou, Meiting Liu +4
Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). By constructing a steering vector from examples o…
Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
Boyi Deng, Xu Wang, Yaoning Wang +15
Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, limiting our ability to inspec…
Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models
Wenhui Tan, Fiorenzo Parascandolo, Enver Sangineto +6
Large Reasoning Models (LRMs) have recently achieved strong mathematical and code reasoning performance through Reinforcement Learning (RL) post-training. However, we show that mod…
Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off
Yu Chen, Yuanhao Liu, Qi Cao
Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representation shifts associated with ja…