12 papers
ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment
Zhengyang Zhao, Shengjie Ye, Lu Ma +3
AI agents are increasingly being tasked with automating AI research itself, particularly the critical post-training phase that transforms base LLMs into aligned assistants. However…
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
DataFlow Team, Bohan Zeng, Daili Hua +39
World models have garnered significant attention as a promising research direction in artificial intelligence, yet a clear and unified definition remains lacking. In this paper, we…
MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning
Xuchen Li, Jing Chen, Xuzhao Li +4
In mathematical reasoning tasks, the advancement of Large Language Models (LLMs) relies heavily on high-quality training data with clearly defined and well-graded difficulty levels…
SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning
Xuchen Li, Ruitao Wu, Xuanbo Liu +17
Recent advances in large language models have enabled AI systems to achieve expert-level performance on domain-specific scientific tasks, yet these systems remain narrow and handcr…
FlipVQA: Scaling Multi-modal Instruction Tuning via Textbook-to-Knowledge Synthesis
Zhen Hao Wong, Jingwen Deng, Yuzhao Wang +6
Textbooks are among the richest repositories of human-verified reasoning knowledge, yet their complex layouts contain multi-column typesetting, cross-page question answer separatio…
MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning
Xukai Wang, Xuanbo Liu, Mingrui Chen +16
With the advancement of powerful large-scale reasoning models, effectively evaluating the reasoning capabilities of these models has become increasingly important. However, existin…
CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding
Yuying Li, Siyi Qian, Hao Liang +6
While Multimodal Large Language Models (MLLMs) have achieved remarkable success in difficult purely textual mathematical reasoning tasks, even advanced closed-source models such as…
DARO: Difficulty-Aware Reweighting Policy Optimization
Jingyu Zhou, Lu Ma, Hao Liang +3
Recent advances in large language models (LLMs) have shown that reasoning ability can be significantly enhanced through Reinforcement Learning with Verifiable Rewards (RLVR). Group…
Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge
Hao Liang, Ruitao Wu, Bohan Zeng +3
Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 s…
LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning
Zhen Hao Wong, Jingwen Deng, Runming He +7
Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning in unfamiliar settings. This discrepancy suggests that standard fine-tuning…
Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions
Lu Ma, Hao Liang, Meiyi Qiang +9
Recent advances in large language model (LLM) reasoning have shown that sophisticated behaviors such as planning and self-reflection can emerge through reinforcement learning (RL).…
Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning
Mingrui Chen, Haogeng Liu, Hao Liang +3
In this work, we investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reas…