# Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual Transactions

arXiv: https://arxiv.org/abs/2609.07675 · HTML: https://mlsanity.com/paper/2609.07675/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark](https://mlsanity.com/paper/2304.03279/) (2023)
- [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making](https://mlsanity.com/paper/2407.06567/) (2024)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents](https://mlsanity.com/paper/2505.02077/) (2025)
- [TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets](https://mlsanity.com/paper/2502.01506/) (2025)
- [The Anatomy of a Cryptocurrency Pump-and-Dump Scheme](https://mlsanity.com/paper/1811.10109/) (2018)
- [Token Spammers, Rug Pulls, and SniperBots: An Analysis of the Ecosystem of Tokens in Ethereum and in the Binance Smart Chain (BNB)](https://mlsanity.com/paper/2206.08202/) (2022)
- [How to Interpret Agent Behavior](https://mlsanity.com/paper/2605.13625/) (2026)
- [Five Attacks on x402 Agentic Payment Protocol](https://mlsanity.com/paper/2605.11781/) (2026)
- [A Midsummer Meme's Dream: Investigating Market Manipulations in the Meme Coin Ecosystem](https://mlsanity.com/paper/2507.01963/) (2025)
- [Unveiling the Risks of NFT Promotion Scams](https://mlsanity.com/paper/2301.09806/) (2023)
- [No Certificate, No Execution: Certified Traces as a Foundation for Trustworthy AI Agents](https://mlsanity.com/paper/2605.24462/) (2026)
- [Securing Agentic AI: From Per-Action Checks to Trajectory Assurance](https://mlsanity.com/paper/2608.01558/) (2026)

## Abstract (arXiv)

Transaction-local controls answer whether one financial request may proceed, but market behavior can be distributed across messages, agents, assets, and time. We study this interpretation gap in a virtual exchange populated by ten role-conditioned language-model agents. The agents communicate, trade reference assets and futures, launch tokens, and manage concentrated-liquidity pools under prescriptive adversarial roles. We analyze eight 72-cycle trajectories across two time-blinded hourly replay paths, with a runner-side wallet policy enabled or disabled. The retained artifacts connect generated outgoing messages, policy events, balances, positions, and cycle-end market state. A focal reconstruction shows a launch--promotion--exit scenario realized across private coordination, public claims, follower positioning, repeatedly withheld exits, and a later non-blocking request aligned with a token balance change. Across policy-enabled runs, the gate withholds direct requests selectively; most policy-categorized candidates are flagged rather than blocked, while the surrounding interaction can continue. Repeated runs also show that category-level and within-trajectory relations can recur even when normalized score-change rankings do not. These findings motivate agent-behavior evaluation that links communication, authorization, and evolving state instead of treating individual transaction verdicts as complete safety judgments.