5 papers
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
NeoHorse Team, Guoliang Cao, Guohao Dai +34
Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into the next round of learning. We p…
From Question Answering to Task Completion: A Survey on Agent System and Harness Design
Jianyuan Guo, Zhiwei Hao, Chengcheng Wang +14
LLM-based agents mark a shift from passive question answering to active task completion: they perceive environments, invoke tools, maintain state, and act over extended horizons. A…
FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools
Shijie Han, Jingshu Zhang, Yiqing Shen +2
Current financial large language models (FinLLMs) struggle with two critical limitations: the absence of objective evaluation metrics to assess the quality of stock analysis report…
QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Models
Changhai Zhou, Yuhua Zhou, Shijie Han +2
The rise of large language models (LLMs) has significantly advanced various natural language processing (NLP) tasks. However, the resource demands of these models pose substantial…
RankAdaptor: Hierarchical Rank Allocation for Efficient Fine-Tuning Pruned LLMs via Performance Model
Changhai Zhou, Shijie Han, Lining Yang +4
The efficient compression of large language models (LLMs) has become increasingly popular. However, recovering the performance of compressed LLMs remains a major challenge. The cur…