15 papers
When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation
Siyang Lyu, Zhijing Sun, Xinghao Chen +3
Chain-of-Thought (CoT) distillation transfers multi-step reasoning from large reasoning models to smaller students, but verbose teacher traces inflate both training and inference c…
What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis
Xinghao Chen, Chak Tou Leong, Wenjin Guo +3
Latent Chain-of-Thought (CoT) internalizes reasoning within continuous hidden states, offering a promising alternative to verbose discrete reasoning traces. However, robust latent…
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
Yuchuan Tian, Mengyu Zheng, Haocheng Mei +5
Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databas…
What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents
Qinghua Xing, Yinda Chen, Yaping Jin +6
Large language model agents increasingly rely on skills: reusable procedural documents encoding workflows, tool use, implementation patterns, validation checks, and domain rules. S…
UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
Yijuan Liang, Xinghao Chen, Yifan Ge +5
Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However, existing research exhibits…
VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
Xiangbo Gao, Sicong Jiang, Bangya Liu +12
As AI-assisted video creation becomes increasingly practical, instruction-guided video editing has become essential for refining generated or captured footage to meet professional…