Category: Papers

1. Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation 🔑 Keywords: Mathematical Reasoning, Reinforcement Learning, Difficulty-Aware Group […]

1. LongCat-Flash-Thinking-2601 Technical Report 🔑 Keywords: Mixture-of-Experts, agentic reasoning, domain-parallel expert training, asynchronous reinforcement learning, real-world noise 💡 Category: Knowledge Representation and […]

1. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience 🔑 Keywords: EvoCUA, AI Native, Policy Optimization, Data Generation, Evolutionary […]

1. Agentic Reasoning for Large Language Models 🔑 Keywords: Agentic reasoning, Large language models, Autonomous agents, Reinforcement learning, Real-world applications 💡 Category: […]

1. Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization 🔑 Keywords: Vision-Language-Action, cross-embodiment generalization, human-centric learning, Mixture-of-Transformers, multimodal data 💡 Category: Robotics […]

1. ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development 🔑 Keywords: Large Language Models, agentic backend coding, executable workflow, development lifecycle, containerized […]

1. Urban Socio-Semantic Segmentation with Vision-Language Reasoning 🔑 Keywords: socio-semantic segmentation, vision-language model, reinforcement learning, cross-modal recognition, SocioSeg 💡 Category: Multi-Modal Learning […]

1. Controlled Self-Evolution for Algorithmic Code Optimization 🔑 Keywords: Controlled Self-Evolution, feedback-guided genetic evolution, initialization bias, Hierarchical Evolution Memory, LLM backbones 💡 […]

1. GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization 🔑 Keywords: Multi-reward reinforcement learning, GRPO, GDPO, training stability 💡 Category: […]

1. Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting 🔑 Keywords: Entropy-Adaptive Fine-Tuning, catastrophic forgetting, token-level entropy, epistemic uncertainty, knowledge conflict 💡 […]

1. Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits 🔑 Keywords: Large Language Models, Gnosis, Self-Awareness, Intrinsic Self-Verification, Zero-Shot 💡 […]

1. Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling 🔑 Keywords: Retrieval-Augmented Generation, LLMs, Hypergraph-Based Memory, Complex Reasoning, Global […]