6 papers
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…
SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
Hongye Cao, Sijia Jing, Yanming Wang +14
With the rapid advancement of Large Language Models (LLMs), the safety of LLMs has been a critical concern requiring precise assessment. Current benchmarks primarily concentrate on…
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…
Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation
Hongye Cao, Fan Feng, Jing Huo +4
Model-based offline Reinforcement Learning (RL) constructs environment models from offline datasets to perform conservative policy optimization. Existing approaches focus on learni…
Causal Information Prioritization for Efficient Reinforcement Learning
Hongye Cao, Fan Feng, Tianpei Yang +2
Current Reinforcement Learning (RL) methods often suffer from sample-inefficiency, resulting from blind exploration strategies that neglect causal relationships among states, actio…
Towards Empowerment Gain through Causal Structure Learning in Model-Based RL
Hongye Cao, Fan Feng, Meng Fang +4
In Model-Based Reinforcement Learning (MBRL), incorporating causal structures into dynamics models provides agents with a structured understanding of the environments, enabling eff…