11 papers
Rethinking Normalization Placement for LLMs: Post-Norm under Curriculum Depth Growing
Sheng Ren, Yadong Wang, Naiqiang Tan +7
Pre-norm is the standard normalization placement in modern Transformers because it facilitates joint optimization of full-depth models. We ask whether this preference persists when…
Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning Models
Yingsha Xie, Tiansheng Huang, Enneng Yang +5
Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety alignment for an LRM are usually const…
Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning
Qin-Wen Luo, Sheng Ren, Xiang Chen +4
Chain-of-Thought (CoT) has substantially empowered Large Language Models (LLMs) to tackle complex reasoning tasks, yet the verbose nature of explicit reasoning steps incurs prohibi…
Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System
Yanming Li, Xuelin Zhang, WenJie Lu +11
Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving complex problems. However, training…
SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment
Xianya Fang, Xianying Luo, Yadong Wang +8
Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e…
UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
Haotian Luo, Huaisong Zhang, Xuelin Zhang +15
Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical…
D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents
Hongze Mi, Yibo Feng, Wenjie Lu +12
Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by s…
Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
Haotian Luo, Haiying He, Yibo Wang +6
Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern.…
R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search
Yibo Wang, Haotian Luo, Huanjin Yao +8
Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by enabling step-by-step problem-solving, yet its extension to Long-CoT introduces substantial computational…
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Haotian Luo, Li Shen, Haiying He +6
Recently, long-thought reasoning LLMs, such as OpenAI's O1, adopt extended reasoning processes similar to how humans ponder over complex problems. This reasoning paradigm significa…
Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
Yibo Wang, Tiansheng Huang, Li Shen +6
Harmful fine-tuning attack introduces significant security risks to the fine-tuning services. Main-stream defenses aim to vaccinate the model such that the later harmful fine-tunin…