build1 publisher
CLQT measures a 0.30 gap between what LLM trading agents say and what they allocate
Bo Qu and Mingguang Chen seal every gather-analyze-decide-execute-reflect cycle into a recompute-verifiable audit chain and score five capability axes from it. In four weeks of live paper trading the gap came to 0.23.
Publishers:arxiv.org
Reality
- Evidence46
- Adoption12
- Hype gap−15
- Incentives45
- Confidence60