22 papers
Quantization Degradation in Large Language Models: A Signal-Noise Perspective
Chenxi Zhou, Pengfei Cao, Jinyu Ye +5
Post-training quantization reduces the deployment cost of large language models, yet how severely a quantized model degrades is not determined by bit-width alone. We systematically…
SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs
Kejian Zhu, Zhuoran Jin, Shangqing Tu +5
Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enhancing multi-task reasoning for large language models (LLMs). Our preli…
Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning
Kejian Zhu, Zhuoran Jin, Dongqi Huang +4
Recent works train agents by constructing large-scale multimodal environment pools. However, we find that simply increasing the number of multimodal environments does not always be…
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
Tianyi Men, Zhuoran Jin, Kang Liu +1
Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are trained on uncontrollable and opa…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Shuqi Lu, Chaofan Li, Kun Luo +21
Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed i…
LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis
Chenhao Yuan, Yinhao Xu, Shuwen Xu +8
Synthesizing long-context supervised fine-tuning (SFT) data is a scalable way to enhance the long-context understanding of large language models (LLMs), yet existing approaches sha…