Category: Papers

1. On Data Engineering for Scaling LLM Terminal Capabilities 🔑 Keywords: Terminal Agent, Synthetic Task Generation, Data Engineering, Curriculum Learning 💡 Category: […]

1. A Very Big Video Reasoning Suite 🔑 Keywords: Video Reasoning, Large-scale Dataset, Spatiotemporal Reasoning, VBVR, Emergent Generalization 💡 Category: Knowledge Representation […]

1. VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training 🔑 Keywords: Variational sEquence-level Soft Policy Optimization (VESPO), Variance reduction, […]

1. DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories 🔑 Keywords: DeepImageSearch, agentic paradigm, multimodal retrieval systems, contextual cues, […]

1. Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs 🔑 Keywords: Feature Activation Coverage, data diversity, cross-model knowledge transfer […]

1. The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies 🔑 Keywords: Multi-agent LLM systems, self-evolution trilemma, safety […]

1. Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters 🔑 Keywords: Mixture-of-Experts, agentic intelligence, efficient parameter utilization, optimized attention mechanisms, […]

1. OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions 🔑 Keywords: Large Language Models, autonomous agents, OdysseyArena, transition laws, […]

1. ERNIE 5.0 Technical Report 🔑 Keywords: ERNIE 5.0, Autoregressive Model, Multimodal Understanding, Mixture-of-Experts, Elastic Training 💡 Category: Multi-Modal Learning 🌟 Research […]

1. ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas 🔑 Keywords: ASTRA, tool-augmented language models, multi-step decision making, verifiable reinforcement learning, […]

1. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives 🔑 Keywords: AI-generated summary, Autonomous scientific discovery, large language […]

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