InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language

Create, Evaluate, and Connect AI Skills

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Can We Predict Before Executing Machine Learning Agents?

From Data to Behavior: Predicting Unintended Model Behaviors Before Training

MemP: Exploring Agent Procedural Memory

[ICLR/AAAI 2026] Open-Source LLM-Based Data Analysis Agents