uncategorised

Framework and toolkits for building and evaluating collaborative agents that can work together with humans.

ConcoLLMic: the first language- and theory-agonistic concolic execution engine via LLM agents

A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award)

AAAI24(Oral) ProAgent: Building Proactive Cooperative Agents with Large Language Models

[CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.

A simple yet versatile context engineered for scalable online data collection

[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Agents).

RepairAgent is an autonomous LLM-based agent for software repair.

Socratic is a framework for building reliable vertical AI agents by letting human experts teach agents interactively, turning tacit domain knowledge into a continuously improving knowledge base.

[🏆 CHI26 Best Paper] CoBRA: Reproducible control of LLM agent behavior via classic social science experiments

Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups

[NeurIPS 2024 D&B] VideoGUI: A Benchmark for GUI Automation from Instructional Videos