7 papers · 1 filter
OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills
Qiyuan Liu, Tingfeng Hui, Kun Zhan +2
LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seem…
Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions
Xuan Yang, Hao Xu, Tingfeng Hui +4
Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world scenarios. Such benchmarks m…
STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
Tingfeng Hui, Hao Xu, Pengyu Zhu +5
Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Exis…
LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards
Bowen Ping, Zijun Chen, Yiyao Yu +3
Reinforcement Learning has emerged as a key driver for LLM reasoning. This capability is equally pivotal in long-context scenarios--such as long-dialogue understanding and structur…
DecIF: Improving Instruction-Following through Meta-Decomposition
Tingfeng Hui, Pengyu Zhu, Bowen Ping +4
Instruction-following has emerged as a crucial capability for large language models (LLMs). However, existing approaches often rely on pre-existing documents or external resources…
Smaller Language Models Are Better Instruction Evolvers
Tingfeng Hui, Lulu Zhao, Guanting Dong +3
Instruction tuning has been widely used to unleash the complete potential of large language models. Notably, complex and diverse instructions are of significant importance as they…