5 papers
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning
Siyuan Gan, Jiaheng Liu, Boyan Wang +8
Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from thinking, a long Chain of Thought (Co…
Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning
Hongye Cao, Nuo Yan, Haoyuan Deng +5
Agentic reinforcement learning (RL) equips large language models (LLMs) with tool-use capabilities that substantially improve reasoning on complex tasks. However, integrating exter…
JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data
Junlan Feng, Fanyu Meng, Chong Long +12
We introduce JT-Safe-V2, a large language model designed to advance the safety and trustworthiness of foundation models, extending our previous JT-Safe model toward a more comprehe…
Efficient Reinforcement Learning with Semantic and Token Entropy for LLM Reasoning
Hongye Cao, Zhixin Bai, Ziyue Peng +5
Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this acc…
: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models
Yuanhe Zhang, Xinyue Wang, Haoran Gao +4
Large Language Models (LLMs), due to substantial computational requirements, are vulnerable to resource consumption attacks, which can severely degrade server performance or even c…