Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Zheng Lu

Zheng Lu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2NLP×1ML×1Neural Computing×1

Frequent co-authors

Mingqi Gao1×
Qinlei Xie1×
Wanqi Zhong1×
Hanwen Cui1×
Heng Cao1×
Zirui Song1×

Research Timeline

2026
Compute Allocation in Evolutionary Search: From Depth-Breadth to Multi-Armed Bandits

The paper proposes BaSE, a multi-armed bandit approach, to optimally allocate a fixed budget of LLM calls across parallel evolutionary search trajectories, significantly improving mean fitness and reliability.

Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners

The paper argues that current embodied planning benchmarks prioritize superficial language prediction over true physical reasoning, introducing new benchmarks and a large-scale dataset to demonstrate that physically grounded causal reasoning is necessary for reliable autonomous agents.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentJun 1, 2026

Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners

Zheng Lu, Mingqi Gao, Qinlei Xie, Wanqi Zhong +7 more

The paper argues that current embodied planning benchmarks prioritize superficial language prediction over true physical reasoning, introducing new benchmarks and a large-scale dataset to demonstrate…

View →
cs.CLcs.AIcs.LGRecentMay 28, 2026

Compute Allocation in Evolutionary Search: From Depth-Breadth to Multi-Armed Bandits

Sixue Xing, Haoyu He, Kerui Wu, Zhuo Yang +3 more

The paper proposes BaSE, a multi-armed bandit approach, to optimally allocate a fixed budget of LLM calls across parallel evolutionary search trajectories, significantly improving mean fitness and rel…

View →