complex reasoning
A type of cognitive task that involves drawing inferences, making predictions, or solving problems that require deeper understanding and manipulation of data.
- ARIA: Training Language Agents with Intention-driven Reward Aggregation
- BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
- Controlling Thinking Speed in Reasoning Models
- DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding
- DyFlow: Dynamic Workflow Framework for Agentic Reasoning
- Incentivizing LLMs to Self-Verify Their Answers
- Learning to Better Search with Language Models via Guided Reinforced Self-Training
- Lost in Transmission: When and Why LLMs Fail to Reason Globally
- MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
- MoBA: Mixture of Block Attention for Long-Context LLMs
- PUO-Bench: A Panel Understanding and Operation Benchmark with A Privacy-Preserving Framework
- SPMDM: Enhancing Masked Diffusion Models through Simplifing Sampling Path
- Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
- Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning