Uncertainty-Aware Deferral for LLM Agents: When to Escalate from Small to Large Models
ReDAct defers from a small model to a large one only when perplexity signals uncertainty, cutting cost 64% at matching accuracy for agent workflows.
#decision-making
Вземане на решения
Вземане на решения, основано на данни, с финансови прозрения
InvestorBench: Qwen2.5-72B tops stocks at 46.15% CR
InvestorBench: Qwen2.5-72B leads stock trading at 46.15% CR; finance-tuned Palmyra-Fin backfires on equities—size beats domain fine-tuning.
LATS: Езиков агент с дървовидно търсене — разсъждение, действие и планиране в една рамка
LATS обединява ReAct, Tree of Thoughts и Reflexion в една MCTS рамка, постигайки 92.7% pass@1 на HumanEval с GPT-4.
Tree of Thoughts: Deliberate Problem Solving with LLM Search
Tree of Thoughts hits 74% on Game of 24 where GPT-4 chain-of-thought gets 4%, by searching and backtracking over steps, a pattern finance agents can borrow.