Jingxuan Wu

Identifiers

• name variant Jingxuan Wu 0.60 · backfill

Papers (5)

1. Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents cs.AI · 2026 · author #6
2. Calibration Is Not Control: Why LLM-Agent Oversight Needs Intervention cs.AI · 2026 · author #4
3. Adversarial Dual On-Policy Distillation from Expressive Teacher cs.LG · 2026 · author #2
4. FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning cs.LG · 2025 · author #2
5. Letting Trajectories Spread: Quality-Preserving Control for Diverse Flow Matching cs.AI · 2025 · author #1

Mentions

• 2606.21409 #6 · arxiv_oai · confidence 0.70 Jingxuan Wu
• 2606.21399 #4 · arxiv_oai · confidence 0.70 Jingxuan Wu
• 2510.09222 #2 · arxiv_oai · confidence 0.70 Jingxuan Wu
• 2605.27095 #2 · arxiv_oai · confidence 0.70 Jingxuan Wu
• 2510.09060 #1 · arxiv_oai · confidence 0.70 Jingxuan Wu

Frequent Coauthors

• Xingrui Yu 5 shared papers
• Zhenglin Wan 5 shared papers
• Chubin Zhang 4 shared papers
• Ivor Tsang 4 shared papers
• Bo An 3 shared papers
• Mingcong Lei 2 shared papers
• Pengfei Zhou 2 shared papers
• Wangbo Zhao 2 shared papers
• Yang You 2 shared papers
• Ivor W. Tsang 1 shared papers
• Qi Wen 1 shared papers
• Yaxin Zhou 1 shared papers
• Yuzhe Yang 1 shared papers