PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Latency Arbitrage

• URL: http://arxiv.org/abs/2604.03888v1
• Date: Sat, 04 Apr 2026 22:51:06 GMT
• Title: PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Latency Arbitrage
• Abstract summary: PolySwarm deploys a swarm of 50 diverse LLM personas that concurrently evaluate binary outcome markets.<n>A latency arbitrage module exploits stale Polymarket prices by deriving CEX-implied probabilities from a log-normal pricing model.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper presents PolySwarm, a novel multi-agent large language model (LLM) framework designed for real-time prediction market trading and latency arbitrage on decentralized platforms such as Polymarket. PolySwarm deploys a swarm of 50 diverse LLM personas that concurrently evaluate binary outcome markets, aggregating individual probability estimates through confidence-weighted Bayesian combination of swarm consensus with market-implied probabilities, and applying quarter-Kelly position sizing for risk-controlled execution. The system incorporates an information-theoretic market analysis engine using Kullback-Leibler (KL) divergence and Jensen-Shannon (JS) divergence to detect cross-market inefficiencies and negation pair mispricings. A latency arbitrage module exploits stale Polymarket prices by deriving CEX-implied probabilities from a log-normal pricing model and executing trades within the human reaction-time window. We provide a full architectural description, implementation details, and evaluation methodology using Brier scores, calibration analysis, and log-loss metrics benchmarked against human superforecaster performance. We further discuss open challenges including hallucination in agent pools, computational cost at scale, regulatory exposure, and feedback-loop risk, and outline five priority directions for future research. Experimental results demonstrate that swarm aggregation consistently outperforms single-model baselines in probability calibration on Polymarket prediction tasks.

Related papers

• Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents [0.0]
  We introduce Foresight Arena, the first permissionless, on-chain benchmark for evaluating AI forecasting agents on real-world prediction markets.<n>Performance is measured by the Brier Score and a novel Alpha Score -- proper scoring rules that incentivize honest probability reporting.<n>We show that detecting a true edge of $* = 0.02$ at 80% power requires approximately 350 resolved binary predictions.
  arXiv  Detail & Related papers  (2026-05-01T05:33:10Z)
• Computational Arbitrage in AI Model Markets [73.20636221068352]
  An arbitrageur efficiently allocates inference budget across providers to undercut the market.<n>We show that simple arbitrage strategies generate net profit margins of up to 40%.<n>Our results suggest that arbitrage can be a powerful force in AI model markets with implications for model development, distillation, and deployment.
  arXiv  Detail & Related papers  (2026-03-23T18:00:14Z)
• Forecasting Future Language: Context Design for Mention Markets [81.25011140991566]
  We study how input context should be designed to support accurate prediction in mention markets.<n>We find three insights: (1) richer context consistently improves forecasting performance; (2) market-conditioned prompting (MCP) treats the market probability as a prior and updates it using textual evidence, yields better-calibrated forecasts; and (3) a mixture of the market probability and MCP (MixMCP) outperforms the market baseline.
  arXiv  Detail & Related papers  (2026-02-04T12:43:31Z)
• PredictionMarketBench: A SWE-bench-Style Framework for Backtesting Trading Agents on Prediction Markets [0.0]
  PredictionMarketBench is a SWE-bench-style benchmark for evaluating algorithmic and LLM-based trading agents on prediction markets.<n>PredictionMarketBench standardizes (i) episode construction from raw exchange streams (orderbooks, trades, lifecycle, settlement), (ii) an execution-realistic simulator with maker/taker semantics and fee modeling, and (iii) a tool-based agent interface.<n>We release four Kalshi-based episodes spanning cryptocurrency, weather, and sports. Baseline results show that naive trading agents can underperform due to transaction costs and settlement losses, while fee-aware algorithmic strategies remain competitive in volatile episodes
  arXiv  Detail & Related papers  (2026-01-28T06:41:12Z)
• Design and Empirical Study of a Large Language Model-Based Multi-Agent Investment System for Chinese Public REITs [5.339049926920038]
  This study proposes a large language model (LLM)-driven trading framework based on multiagent collaboration.<n>The system integrates four types of analytical agentsannouncement, event, price momentum, and marketcution analysis from different dimensions.
  arXiv  Detail & Related papers  (2026-01-22T16:35:27Z)
• ZIP-RC: Optimizing Test-Time Compute via Zero-Overhead Joint Reward-Cost Prediction [57.799425838564]
  We present ZIP-RC, an adaptive inference method that equips models with zero-overhead inference-time predictions of reward and cost.<n> ZIP-RC improves accuracy by up to 12% over majority voting at equal or lower average cost.
  arXiv  Detail & Related papers  (2025-12-01T09:44:31Z)
• When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents [74.55061622246824]
  Agent Market Arena (AMA) is the first lifelong, real-time benchmark for evaluating Large Language Model (LLM)-based trading agents.<n>AMA integrates verified trading data, expert-checked news, and diverse agent architectures within a unified trading framework.<n>It evaluates agents across GPT-4o, GPT-4.1, Claude-3.5-haiku, Claude-sonnet-4, and Gemini-2.0-flash.
  arXiv  Detail & Related papers  (2025-10-13T17:54:09Z)
• Your AI, Not Your View: The Bias of LLMs in Investment Analysis [62.388554963415906]
  In finance, Large Language Models (LLMs) face frequent knowledge conflicts arising from discrepancies between their pre-trained parametric knowledge and real-time market data.<n>These conflicts are especially problematic in real-world investment services, where a model's inherent biases can misalign with institutional objectives.<n>We propose an experimental framework to investigate emergent behaviors in such conflict scenarios, offering a quantitative analysis of bias in investment analysis.
  arXiv  Detail & Related papers  (2025-07-28T16:09:38Z)
• Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction [54.21695754082441]
  Multi-step stock price prediction over a long-term horizon is crucial for forecasting its volatility. Current solutions to multi-step stock price prediction are mostly designed for single-step, classification-based predictions. We combine a deep hierarchical variational-autoencoder (VAE) and diffusion probabilistic techniques to do seq2seq stock prediction. Our model is shown to outperform state-of-the-art solutions in terms of its prediction accuracy and variance.
  arXiv  Detail & Related papers  (2023-08-18T16:21:15Z)
• Price Interpretability of Prediction Markets: A Convergence Analysis [6.623653707600985]
  We show that the limiting price converges to the geometric mean of agent beliefs in exponential utility-based markets. We also show that the limiting price can be characterized by systems of equations that encapsulate agent beliefs, risk parameters, and wealth.
  arXiv  Detail & Related papers  (2022-05-18T13:15:11Z)
• Learning who is in the market from time series: market participant discovery through adversarial calibration of multi-agent simulators [0.0]
  In electronic trading markets only the price or volume time series are directly observable. We propose a novel two-step method to train a discriminator that is able to distinguish between "real" and "fake" price and volume time series.
  arXiv  Detail & Related papers  (2021-08-02T06:53:37Z)
• Ensemble Forecasting for Intraday Electricity Prices: Simulating Trajectories [0.0]
  Recent studies have shown that the hourly German Intraday Continuous Market is weak-form efficient. A probabilistic forecasting of the hourly intraday electricity prices is performed by simulating trajectories in every trading window. The study aims to forecast the price distribution in the German Intraday Continuous Market in the last 3 hours of trading, but the approach allows for application to other continuous markets, especially in Europe.
  arXiv  Detail & Related papers  (2020-05-04T10:21:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.