Skip to content

Author

Junxiang Lei

We have 2 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

FORGE: Research-Trajectory Hijacking Attacks on Deep Research Agents

This work presents FORGE (Fabricated Orchestrated Reasoning chain for aGent Exploitation), a two-level attack that combines intra-document reasoning fabrication with inter-document chain coordination to hijack subtask planning.

Yu-Ru Pan, Ziheng Zhang, Junxiang Lei et al. · 1 citation
Review Aug 2026

Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks

Results show that a fixed-weight, self-evolving harness can revise, recover, and accumulate verified approaches while producing structured trajectories for future supervised and reinforcement learning.

Boxiu Li, Zimo Wen, Yijia Fan et al. · 2 citations · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.