27 papers
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…
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
Jiachun Li, Zhuoran Jin, Tianyi Men +12
Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model c…
Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation
Yupu Hao, Zhuoran Jin, Huanxuan Liao +2
Large language models (LLMs) rely on tool use to act as autonomous agents, yet often fail in multi-step execution due to insufficient tool-related knowledge and ineffective knowled…
Towards Atoms of Large Language Models
Chenhui Hu, Pengfei Cao, Yubo Chen +2
The fundamental representational units (FRUs) of large language models (LLMs) remain undefined, limiting further understanding of their underlying mechanisms. In this paper, we int…
Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
Chenxi Zhou, Pengfei Cao, Jiang Li +4
Post-Training Quantization (PTQ) is a critical strategy for efficient Large Language Models (LLMs) deployment. However, existing scaling laws primarily focus on general performance…
Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
Jiachun Li, Pengfei Cao, Zhuoran Jin +6
Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on trainin…