mlsanityData to 7 Oct 2026

TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis

arXiv 2607.19794 ↗First posted 22 Jul 2026cs.CL cs.CE cs.DBcited by 0

On the map: LLM agents and tool use → Financial trading and forecasting agents

Abstract (arXiv)

Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count. We present TriAgent, a multi-agent committee stratified by contextual granularity -- a word-level lexicon (VADER), a sentence-level domain transformer (FinBERT), and a cross-sentence reasoner (Qwen2.5, 0.5B-14B-4bit, with Mistral-7B and Phi-3.5-mini cross-family checks). A three-way Semantic Divergence Index (SDI) measures pairwise disagreement across granularities and routes each query accordingly. Our central finding is the critic plateau: when the LLM is re-tasked as a critic over the smaller agents' outputs, F1 plateaus at ~0.87 across 1.5B-7B Qwen (bootstrap 95% CIs overlap), while a same-size 3-persona vote drops to F1=0.66, which is driven by granularity-stratified diversity. Three corollaries follow from the same SDI signal: (i) a Shared Consensus Dictionary on multilingual sentence-BERT answers 95% of Chinese queries from an English cache at F1=0.99 -- cross-border canonicalization at zero marginal cost; (ii) SDI doubles as a post-hoc LLM-hallucination detector at AUC=0.90; (iii) the SDI single-stage strategy attains the best risk-adjusted return (Sharpe=3.50) on a 20-ticker back-test, dominating both always-FinBERT (1.36) and always-LLM (0.11). At 10M-user scale, TriAgent saves 9.3M/year vs. a GPT-4o-mini baseline. Code, lexicons, and the SCD are released.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 26 of its 33 references that are in the map. First posted on arXiv 22 Jul 2026.

Builds on

26 of 33 references.

References · 26

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2023A Survey of Large Language Modelscited by 2,537
  6. 2017Billion-scale similarity search with GPUscited by 2,477
  7. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  9. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  10. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  11. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  12. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
14 more
  1. 2023BloombergGPT: A Large Language Model for Financecited by 923
  2. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  3. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  4. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  5. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  6. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  7. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  8. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  9. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 378
  10. 2013Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Textscited by 310
  11. 2023FinGPT: Open-Source Financial Large Language Modelscited by 244
  12. 2023PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Financecited by 217
  13. 2023Large Language Model Routing with Benchmark Datasetscited by 166
  14. 2020FinBERT: A Pretrained Language Model for Financial Communicationscited by 161

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Designing Heterogeneous LLM Agents for Financial Sentiment Analysis
  2. 2026FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit Deliberation
  3. 2025TradingGroup: A Multi-Agent Trading System with Self-Reflection and Data-Synthesis
  4. 2025Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis
  5. 2025FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis
  6. 2025MASFIN: A Multi-Agent System for Decomposed Financial Reasoning and Forecasting
  7. 2025Adaptive Financial Sentiment Analysis for NIFTY 50 via Instruction-Tuned LLMs , RAG and Reinforcement Learning Approaches
  8. 2026SenseAI: A Human-in-the-Loop Dataset for RLHF-Aligned Financial Sentiment Reasoning