8 papers
Do LLMs Know Their Vulnerable Scenarios?
Ziheng Peng, Huiqi Deng, Haoran Jing +5
Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teami…
SkillEval: Decomposing Agent Skill Quality into Interpretable Signals
Jiahui Han, Qinuo Li, Ziheng Peng +6
Agent skills provide reusable knowledge that helps agents solve specialized tasks. As their use expands, evaluating skill quality becomes increasingly important. Existing evaluatio…
Self-Improving Large Language Models via Progressive Experience Evolution
Shijie Ren, Xiting Wang, Meng Li +8
Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transforming transient interaction expe…
To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
Wei Shi, Ziheng Peng, Sihang Li +4
LLM agents exhibit a consistent tendency to over-call, invoking tools even in situations where none is needed. On the When2Call benchmark, six models from three families show high…
Target Concept Tuning Improves Extreme Weather Forecasting
Shijie Ren, Xinyue Gu, Ziheng Peng +6
Deep learning models for meteorological forecasting often fail in rare but high-impact events such as typhoons, where relevant data is scarce. Existing fine-tuning methods typicall…
DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection
Hai Ci, Ziheng Peng, Pei Yang +2
Diffusion-based editing enables realistic modification of local image regions, making AI-generated content harder to detect. Existing AIGC detection benchmarks focus on classifying…
ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting
Ziheng Peng, Shijie Ren, Xinyue Gu +3
While deep learning has achieved impressive performance in time series forecasting, it becomes increasingly crucial to understand its decision-making process for building trust in…
CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay
Jianshu Zhang, Yankai Fu, Ziheng Peng +2
This paper introduces a novel perspective to significantly mitigate catastrophic forgetting in continuous learning (CL), which emphasizes models' capacity to preserve existing know…