5 papers
Skip-Connected Policy Optimization for Implicit Advantage
Fengwei Teng, Jinyi Bai, Xinhao Yao +3
Group Relative Policy Optimization (GRPO) has proven effective in RLVR by using outcome-based rewards. While fine-grained dense rewards can theoretically improve performance, we re…
The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View
Xinhao Yao, Lu Yu, Xiaolin Hu +4
The ongoing debate on whether reinforcement learning with verifiable rewards (RLVR) expands or shrinks the reasoning capabilities of large language models (LLMs) remains unresolved…
Atom of Thoughts for Markov LLM Test-Time Scaling
Fengwei Teng, Quan Shi, Zhaoyang Yu +4
Large Language Models (LLMs) have achieved significant performance gains through test-time scaling methods. However, existing approaches often incur redundant computations due to t…
Self-Supervised Prompt Optimization
Jinyu Xiang, Jiayi Zhang, Zhaoyang Yu +8
Well-designed prompts are crucial for enhancing Large language models' (LLMs) reasoning capabilities while aligning their outputs with task requirements across diverse domains. How…
AFlow: Automating Agentic Workflow Generation
Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu +11
Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed i…