Marketing Manager
The BIRD benchmark (NeurIPS 2023) tests LLMs on 95 real databases — GPT-4 reaches only 54.89% execution accuracy with domain hints and 34.88% without, a 20-point gap that directly shapes what a natural-language BQL interface for Beancount would need to solve.
CMU and NC State researchers propose using System-Theoretic Process Analysis (STPA) and a capability-enhanced Model Context Protocol to derive formal safety specifications for LLM agent tool use, with Alloy-based verification demonstrating absence of unsafe flows in a calendar scheduling case study.
Microsoft's GraphRAG builds a Leiden-partitioned entity graph over a text corpus and precomputes community summaries to answer global sensemaking questions that standard vector RAG cannot handle — but a 2025 bias audit shows its 72–83% win rates collapse after correcting for position and length artifacts in LLM-as-judge evaluation.
FinAuditing tests 13 LLMs zero-shot on 1,102 real SEC XBRL filing instances; top scores are 13.86% on financial math verification and 12.42% on concept retrieval—results that directly bound what AI accounting tools can be trusted to automate without external tooling.
InvestorBench (ACL 2025) tests 13 LLM backbones on backtested stock, crypto, and ETF trading using cumulative return and Sharpe ratio — not QA accuracy. Qwen2.5-72B tops the stock leaderboard at 46.15% CR; finance-tuned models backfire on equities. Model size predicts performance more reliably than domain fine-tuning.
StructRAG (ICLR 2025) routes each query to a task-appropriate structure type — table, graph, catalogue, algorithm, or chunk — before reasoning, scoring 28 points higher than GraphRAG on the Loong benchmark while running 22× faster, with the DPO-trained router alone accounting for a 15-point accuracy gain.
A 2026 Stanford preprint equalizes thinking-token budgets across five multi-agent architectures and finds single-agent LLMs match or beat multi-agent systems on multi-hop reasoning — with theoretical grounding in the Data Processing Inequality and implications for finance AI agent design.
M3MAD-Bench stress-tests Multi-Agent Debate across 9 models, 5 domains, and vision-language settings, finding that Collective Delusion causes 65% of failures, adversarial debate cuts accuracy by up to 12.8%, and Self-Consistency typically matches debate accuracy at lower token cost.
AGrail (ACL 2025) introduces a two-LLM cooperative guardrail that adapts safety checks at inference time via test-time adaptation, achieving 0% prompt injection attack success and 95.6% benign action preservation on Safe-OS — compared to GuardAgent and LLaMA-Guard blocking up to 49.2% of legitimate actions.
ShieldAgent (ICML 2025) replaces LLM-based guardrails with probabilistic rule circuits built on Markov Logic Networks, achieving 90.4% accuracy on agent attacks with 64.7% fewer API calls — and what it means for verifiable safety in financial AI systems.
Atlas (JMLR 2023) achieves 42.4% accuracy on Natural Questions with only 64 training examples—beating PaLM 540B by 3 points using 11B parameters—by jointly pre-training a Contriever-based dense retriever with a T5 Fusion-in-Decoder reader. Analysis covers retrieval accuracy limits, 587GB index infrastructure costs, and implications for Beancount ledger QA systems.
Izacard and Grave's FiD architecture independently encodes retrieved passages then fuses them in the decoder, outperforming RAG-Sequence by 4–11 points on NQ and TriviaQA. This post examines the design and its implications for Beancount ledger QA, where multi-entry synthesis across transactions is the norm.
