arXiv · arXiv · 2025
We study opportunistic optimal liquidation over fixed deadlines on BTC-USD limit-order books (LOB). We present RL-Exec, a PPO agent trained on historical replays augmented with endogenous transient impact (resilience), partial fills, maker/taker fees, and latency. The policy observes depth-20 LOB features plus microstructure indicators and acts under a sell-only inventory constraint to reach a residual target. Evalua…
Enzo Duflot, Stanislas Robineau
arXiv · arXiv · 2026
AI agents can select tools, counterparties, and transaction parameters, yet inference should not itself confer authority to execute a financial action. This study develops and evaluates Authority-Inference Separation (AIS), an intent-centered architecture for bounded agentic finance. AIS treats a financial action intent as the control object: a machine-generated proposal can receive temporary executable authority onl…
Hui Gong, Michail Samawi, Francesca Medda
arXiv · arXiv · 2019
We show how a multi-agent simulator can support two important but distinct methods for assessing a trading strategy: Market Replay and Interactive Agent-Based Simulation (IABS). Our solution is important because each method offers strengths and weaknesses that expose or conceal flaws in the subject strategy. A key weakness of Market Replay is that the simulated market does not substantially adapt to or respond to the…
Tucker Hybinette Balch, Mahmoud Mahfouz, Joshua Lockhart, Maria Hybinette, David Byrd
arXiv · arXiv · 2026
Automated execution algorithms are organized into schedule-based and liquidity-seeking families. This paper concerns the first, whose members -- Time-Weighted Average Price (TWAP), Volume-Weighted Average Price (VWAP), Percentage of Volume (POV) and Implementation Shortfall -- are all model-based: each derives its decisions from an explicit model, forecast, schedule or control rule. We introduce Shadow-PPOV, a passiv…
Vincent Maciejewski
arXiv · arXiv · 2026
Trader-facing dynamic fees are increasingly proposed for automated market makers (AMMs), but historical data do not identify how order flow would respond: trader-facing fees do not vary, trader types are latent, and a replayed tape is not a sequential decision environment. We therefore construct a minimal closed-loop simulator in which the missing signal exists by construction: two constant-product pools repriced by …
Wen-Ting Wang
arXiv · arXiv · 2026
The label event-linked perpetual often conflates mathematically different contracts. We replace a flat product list with a four-axis taxonomy: underlying geometry, temporal structure, settlement structure, and venue-oracle composition. The taxonomy covers a single binary probability, conditional ratios, event spreads, baskets, path functionals, liquidity indices, rolling sequences, and flow-only swaps. We derive a co…
Maksym Nechepurenko
arXiv · arXiv · 2026
Prediction markets offer a natural testbed for trading agents: contracts have binary payoffs, prices can be interpreted as probabilities, and realized performance depends critically on market microstructure, fees, and settlement risk. We introduce PredictionMarketBench, a SWE-bench-style benchmark for evaluating algorithmic and LLM-based trading agents on prediction markets via deterministic, event-driven replay of h…
Avi Arora, Ritesh Malpani
arXiv · arXiv · 2020
Optimal order execution is widely studied by industry practitioners and academic researchers because it determines the profitability of investment decisions and high-level trading strategies, particularly those involving large volumes of orders. However, complex and unknown market dynamics pose significant challenges for the development and validation of optimal execution strategies. In this paper, we propose a model…
Michaël Karpe, Jin Fang, Zhongyao Ma, Chen Wang