Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Zhan Shi
Observed name:
Shi, Zhan
Institutions:
Amazon (United States),
Michigan State University
Observed institutions:
Amazon (United States),
Michigan State University
OpenAlex ID:
A5137607334
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
2026
·
Minhua Lin
, Juncheng Wu
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
48
PDF
Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
2026
·
Liu, Zewen
, Shi, Zhan
, et al.
·
arXiv (Cornell University)
·
34
PDF
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
2026
·
Tianxin Wei
, Zhan Shi
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
·
26
PDF
How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
2026
·
Cui, Yingqian
, Dai, Zhenwei
, et al.
·
arXiv (Cornell University)
·
11
PDF
TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards
2026
·
Sun, Rui
, Shi, Zhan
, et al.
·
arXiv (Cornell University)
PDF
A Reward-Guided Dual-Phase Framework for Adaptive Inference-Time Reasoning
2026
·
Association for Computational Linguistics 2026
, Cui, Yingqian
, et al.
·
Underline Science Inc.
Show more works
View as search
Works count:
6
Citation count:
119
H-index:
4
I10-index:
4
Year
Topic
Type
