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
13Unique collaborators
2/2Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2282896192
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Yichao Fu (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Adoption: 2 papers
- Productivity: 2 papers
- Labor Markets: 1 paper
Claim outcomes
- Other: 2 papers
- Firm Productivity: 2 papers
- Output Quality: 1 paper
- Adoption Rate: 1 paper
- Ai Safety And Ethics: 1 paper
- Error Rate: 1 paper
- Task Allocation: 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 production-aligned benchmark finds leading LLM kernel agents fail to improve real-world inference speed: the best agent is 6% slower than hardened systems while others perform markedly worse. FastKernels—covering 46 representative architectures and matching production interfaces—highlights benchmark-production misalignment as a key bottleneck to deploying agent-generated kernels.arxiv | Yichao Fu provider id |
2026-05-22 | 1 |
| A feedback-grounded training method meaningfully boosts long-horizon LLM-agent performance—raising Pass@k up to 14% versus strong baselines—by teaching models how to recover from failures rather than only optimizing final success. The approach increases sample efficiency, implying firms can extract more performance from the same interaction logs and reduce marginal interaction costs.arxiv | Yichao Fu provider id |
2026-03-17 | 1 |
Citation observation summary
Semantic Scholar supplied counts for 2 of 2 papers in this view; 0 are missing. The observed paper counts sum to 2 cumulative citations. This is a coverage summary, not an author score or h-index.