Tag: AI research agent
Browse our exclusive articles!
AcademiClaw: Benchmarking AI on Complex Academic Tasks
Discover AcademiClaw, a new benchmark challenging AI agents with 80 complex academic tasks from students, advancing AI's real-world capabilities.
Training Large Language Models for Long-Horizon Tasks
Explore how horizon length impacts training dynamics of large language models and improves performance in long-horizon tasks.
How Graphs Enhance Large Language Models’ Accuracy
Discover how integrating graph structures improves large language models by reducing errors and boosting reasoning and data understanding.
Measuring AI Reasoning: Process-Based Evaluation Guide
Discover a new framework for measuring AI reasoning beyond final answers, focusing on intermediate steps and adaptive evaluation methods.
Evaluating LLMs on 1M-Token Contexts for Classical Chinese
Explore LLM performance on 1M-token context windows with retrieval and multi-hop reasoning in classical Chinese texts. Key insights on model accuracy and d...