Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents
Paper • 2510.24702 • Published • 32
Unlearning of LLMs
university
AI & ML interests
None defined yet.
yuexiang96
authored 4
papers 10 months ago
The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
Paper • 2510.25726 • Published • 48
Simulating Environments with Reasoning Models for Agent Training
Paper • 2511.01824 • Published • 2
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
Paper • 2512.07783 • Published • 41
yuexiang96
authored 14
papers over 1 year ago
Small Models Struggle to Learn from Strong Reasoners
Paper • 2502.12143 • Published • 40
Evaluating Vision-Language Models as Evaluators in Path Planning
Paper • 2411.18711 • Published
VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search
Paper • 2503.10582 • Published • 25
Scaling Evaluation-time Compute with Reasoning Models as Process Evaluators
Paper • 2503.19877 • Published • 2
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge
Paper • 2504.10342 • Published • 11
Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
Paper • 2504.12329 • Published
Overtrained Language Models Are Harder to Fine-Tune
Paper • 2503.19206 • Published • 2
The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think
Paper • 2505.10185 • Published • 26
VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation
Paper • 2506.03930 • Published • 27
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Paper • 2507.00432 • Published • 79
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations
Paper • 2504.00824 • Published • 43
Demystifying Long Chain-of-Thought Reasoning in LLMs
Paper • 2502.03373 • Published • 57
Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
Paper • 2501.17703 • Published • 58
Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
Paper • 2501.13826 • Published • 24
yuexiang96
authored 2
papers almost 2 years ago