#decision-making
Data-driven decision making with financial insights
ReDAct runs a small model by default and escalates to an expensive model only when token-level perplexity signals uncertainty, achieving 64% cost savings over GPT-5.2-only while matching or exceeding its accuracy — a directly applicable pattern for Beancount transaction-categorization agents.
InvestorBench: Qwen2.5-72B leads stock trading at 46.15% CR; finance-tuned Palmyra-Fin backfires on equities—size beats domain fine-tuning.
LATS (Language Agent Tree Search, ICML 2024) unifies ReAct, Tree of Thoughts, and Reflexion in a single MCTS framework, reaching 92.7% pass@1 on HumanEval with GPT-4. For git-backed Beancount ledgers, the state-reversion requirement that constrains LATS in production is trivially satisfied.
Tree of Thoughts (ToT) achieves 74% on Game of 24 vs 4% for standard GPT-4 CoT by organizing LLM reasoning into a branching search tree with pruning and backtracking — with direct implications for multi-step financial classification and tax optimization in Beancount workflows.
