Papers, wiki, Option Blackboard, encyclopedia, and cards.
This paper argues that AI-agent alignment in markets should not be understood only as a property of agents, but also as a property of the interaction infrastructure in which agents act. In financial markets, this infrastructure is the market core: the rule system that determines how orders enter, interact, match, persist, and stabilize. If this fundamental interaction layer allows or rewards undesired behaviour, then…
Accurately measuring portfolio similarity is critical for a wide range of financial applications, including Exchange-traded Fund (ETF) recommendation, portfolio trading, and risk alignment. Existing similarity measures often rely on exact asset overlap or static distance metrics, which fail to capture similarities among the constituents (e.g., securities within the portfolio) as well as nuanced relationships between …
The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF), frequently induce model sycophancy, while execution-based environments suffer from adversarial "Test Evasion" by unconstrained agents. In this paper, we introduce an objective alignment pa…
Recent works have increasingly applied Large Language Models (LLMs) as agents in financial stock market simulations to test if micro-level behaviors aggregate into macro-level phenomena. However, a crucial question arises: Do LLM agents' behaviors align with real market participants? This alignment is key to the validity of simulation results. To explore this, we select a financial stock market scenario to test behav…
We investigate portfolio optimization in financial markets from a trading and risk management perspective. We term this task Risk-Aware Trading Portfolio Optimization (RATPO), formulate the corresponding optimization problem, and propose an efficient Risk-Aware Trading Swarm (RATS) algorithm to solve it. The key elements of RATPO are a generic initial portfolio P, a specific set of Unique Eligible Instruments (UEIs),…
The proliferation of Large Language Models (LLMs) is challenged by hallucinations, critical failure modes where models generate non-factual, nonsensical or unfaithful text. This paper introduces Semantic Divergence Metrics (SDM), a novel lightweight framework for detecting Faithfulness Hallucinations -- events of severe deviations of LLMs responses from input contexts. We focus on a specific implementation of these L…
We study the problem of optimal liquidity withdrawal for a representative liquidity provider (LP) in an automated market maker (AMM). LPs earn fees from trading activity but are exposed to impermanent loss (IL) due to price fluctuations. While existing work has focused on static provision and exogenous exit strategies, we characterise the optimal exit time as the solution to a stochastic control problem with an endog…
We study the economic viability of liquidity provision in decentralised exchanges (DEXs) within a structural framework in which market outcomes are endogenous. We formulate strategic interactions as a sequential game: a risk-averse liquidity provider (LP) sets the supply of liquidity in the DEX and a costly dynamic replication strategy in a centralised exchange (CEX), price-sensitive traders determine trading volumes…
As decentralized finance (DeFi) evolves, distinguishing between user behaviors - liquidity provision versus active trading - has become vital for risk modeling and on-chain reputation. We propose a behavioral scoring framework for Uniswap that assigns two complementary scores: a Liquidity Provision Score that assesses strategic liquidity contributions, and a Swap Behavior Score that reflects trading intent, volatilit…
We develop a new framework to detect wash trading in crypto assets through real-time liquidity fluctuation. We propose that short-term price jumps in crypto assets results from wash trading-induced liquidity fluctuation, and construct two complementary liquidity measures, liquidity jump (size of fluctuation) and liquidity diffusion (volatility of fluctuation), to capture the behavioral signature of wash trading. Usin…
Modern portfolio management increasingly demands a balance between traditional risk-adjusted returns and strict Environmental, Social, and Governance (ESG) mandates. Current Reinforcement Learning (RL) approaches typically optimize for a single ESG provider, neglecting the significant divergence in rating methodologies across the industry and the unintuitive nature of manually weighting conflicting objectives. This p…
This paper introduces a transformative framework for managing path-dependent financial risk by shifting from traditional distribution-centric models to a geometry-based approach. We propose the SigSwap as a new regulatory instrument that allows market participants to decompose complex risk into terminal price law and the underlying texture of the price path. By utilising the mathematical properties of the path-signat…
This paper presents a meta-learning framework for credit risk assessment of Italian Small and Medium Enterprises (SMEs) that explicitly addresses the temporal misalignment of credit scoring models. The approach aligns financial statement reference dates with evaluation dates, mitigating bias arising from publication delays and asynchronous data sources. It is based on a two-step temporal decomposition that at first e…
Multi-strategy hedge funds face a fundamental organizational choice: should analysts generating trading strategies communicate, and if so, how? We investigate this using 5-agent LLM-based trading systems across 450 experiments spanning 21 months, comparing five organizational structures from isolated baseline to collaborative and competitive conversation. We show that communication improves performance, but optimal c…
The Dynamic Function Market Maker (DFMM) introduced a fully automated framework for operating a multi-asset market, wherein an algorithmic accounting asset was used to connect different liquidity pools and ensure efficient rebalancing of risks, and internal accounting processes. In the DFMM design, this asset was not tradaeble; however, in this work, we explore the characteristics of this asset, if it were to be made…
In financial markets, a sequential policy that reacts systematically to price movements may become predictable to other market participants. This paper studies whether large language model (LLM) agents exhibit such directional structure through RetailAgent, an experimental framework in which an LLM observes anonymized intraday equity price histories and permitted state, then repeatedly chooses long (hold the stock) o…
Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs). However, existing approaches remain confined to a market-agnostic, supervised learning paradigm that relies on limited, static and human-annotated datasets, and thus are incapable of adapting to evolving market conditions. To address this limitation, we introduce FinSM…
Attention builds a weighted average of values, with weights from a compatibility function of queries and keys. It lets a model focus on relevant parts of a context instead of a single fixed vector.
RLHF fits a reward model to human (or AI) preference comparisons, then optimizes a language model against that reward, usually with a KL penalty back to a reference policy.