MC
Mingju Chen
cs.AIcs.CLcs.LGcs.MA
On Valency
published · living versionsW_v47c5d4w·v1 · currentpublished
DeliverBench: Benchmarking AI Agents on Delivering Realistic Multi-Stage Professional Projects
with Yumou Liu, Zhoufutu Wen, Qianyu Yang, Zijie Wang +19
1 version
Preprints & journals
7 papers in the corpus · 2026AGAR: a reinforcement learning substrate for LLM program evolution2610.09215v1 · Haoran Li, Zengle Ge, Xiaomin Yuan et al.2026 · 0 citationsarXiv
RLDISCOVER: LLM-driven co-evolution of reinforcement learning algorithms2610.09218v1 · Haoran Li, Zengle Ge, Xiaomin Yuan et al.2026 · 0 citationsarXiv
Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents2609.33391v1 · Mingju Chen, Can Lv, Jinrong Liu et al.2026 · 0 citationsarXiv
TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents2608.16156v2 · Huan Zhang, Mingju Chen, Dongxu Zhou et al.2026 · 0 citationsarXiv
Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning2606.03361v2 · Can Lv, Mingju Chen, Heng Chang et al.2026 · 0 citationsarXiv
HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems2606.01779v1 · Mingju Chen, Can Lv, Guibin Zhang et al.2026 · 0 citationsarXiv
A-MapReduce: Executing Wide Search via Agentic MapReduce2602.01331v2 · Mingju Chen, Guibin Zhang, Heng Chang et al.2026 · 0 citationsarXiv
Career total: 8 works. 7 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.