Direction, evidence grade, and study type are AI-generated labels (gpt-5-mini), not human-verified. Syntheses are LLM-written. "Tensions" are machine-detected candidates, not confirmed contradictions. A research-acceleration tool, not peer review.
How this is built →
2Distinct papers
22Unique collaborators
2/2Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2290138488
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Zhikai Lei (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 2 papers
- Productivity: 2 papers
- Adoption: 1 paper
Claim outcomes
- Output Quality: 2 papers
- Other: 1 paper
- Organizational Efficiency: 1 paper
- Decision Quality: 1 paper
- Task Allocation: 1 paper
- Training Effectiveness: 1 paper
Papers in the Semantic Scholar view
Latest stored Semantic Scholar author observations only. Citation counts below are from the same provider and are not combined with other services.
Scroll the table horizontally to see every column.
| Paper | Author evidence | Date | Provider citations |
|---|---|---|---|
| A recursive oversight system lets non-expert users steer LLMs to produce near-expert product requirements, yielding a 54% alignment gain on web-development tasks; the approach can be optimized through reinforcement learning using only online user feedback.arxiv | Zhikai Lei provider id |
2026-02-04 | 0 |
| A new executable benchmark finds state-of-the-art LLM agents often fail real-world backend engineering tasks; across 224 repository-level problems spanning 8 languages and 19 frameworks, agents struggle to configure, containerize and pass end‑to‑end API tests, revealing limits to their readiness for practical backend work.arxiv | Zhikai Lei provider id |
2026-01-16 | 3 |
Citation observation summary
Semantic Scholar supplied counts for 2 of 2 papers in this view; 0 are missing. The observed paper counts sum to 3 cumulative citations. This is a coverage summary, not an author score or h-index.