9 papers
BranPO: Scalable Contrastive Branch Sampling for Long-Horizon Agentic Reinforcement Learning
Yubao Zhao, Weiquan Huang, Sudong Wang +4
Agentic reinforcement learning enables large language models to perform multi-turn planning and tool use, but long-horizon training remains challenging under sparse trajectory-leve…
AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning
Ziye Chen, Hongbin Lin, Chenyu Zhang +3
Zeroth-order (ZO) optimization enables large-language-model fine-tuning without storing backpropagation activations, while LoRA supplies compact trainable adapters. Combining them…
FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline
Haotian Wu, Shufan Jiang, Chios Chen +5
As large language models (LLMs) advance in role-playing (RP) tasks, existing benchmarks quickly become obsolete due to their narrow scope, outdated interaction paradigms, and limit…
Controllable Concept Bottleneck Models
Hongbin Lin, Chenyang Ren, Juangui Xu +7
Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most prev…
Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models
Haotian Wu, Bo Xu, Yao Shu +2
Reasoning large language models (RLLMs) have recently demonstrated remarkable capabilities through structured and multi-step reasoning. While prior research has primarily focused o…
RIMO: An Easy-to-Evaluate, Hard-to-Solve Olympiad Benchmark for Advanced Mathematical Reasoning
Ziye Chen, Chengwei Qin, Yao Shu
As large language models (LLMs) reach high scores on established mathematical benchmarks, such as GSM8K and MATH, the research community has turned to International Mathematical Ol…