Tianrui Qin

Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution

TaskCraft: Automated Generation of Agentic Tasks

A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

Compressed Step Information Memory for End-to-End Agent Foundation Models

Invisible and Adaptive Training-Phase Target-Conditioned Backdoors

APBench: A Unified Benchmark for Availability Poisoning Attacks and Defenses

Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks