activity
20242026
most citedEquilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models

1 citations · 1 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI2026

SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution

Xiachong Feng, Yi Jiang, Xiaocheng Feng +9

Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents. Training such agents via reinforcement learni…

cs.AI2026

Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play

Xiachong Feng, Deyi Yin, Xiaocheng Feng +9

Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adapti…

cs.AI2026

Exploring Reasoning Reward Model for Agents

Kaixuan Fan, Kaituo Feng, Manyuan Zhang +7

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse…

cs.AI2025

QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems

Yiliu Yang, Yilei Jiang, Qunzhong Wang +5

Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural la…

cs.AI2025

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs

Jiakang Yuan, Tianshuo Peng, Yilei Jiang +8

Logical reasoning is a fundamental aspect of human intelligence and an essential capability for multimodal large language models (MLLMs). Despite the significant advancement in mul…

cs.AI20251 cited

Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models

Yingshui Tan, Yilei Jiang, Yanshi Li +6

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving th…