8 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…
Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models
Jinhao Wu, Shiduo Zhang, Yicheng Liu +9
Most vision-language-action (VLA) models map observations directly to actions without explicit intermediate planning, which limits performance on long-horizon tasks where early mis…
Multi-Agent Reinforcement Learning with Communication-Constrained Priors
Guang Yang, Tianpei Yang, Jingwen Qiao +4
Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems. However, in most real-world scenarios, lossy communication is a pr…
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…