mlsanityData to 14 Oct 2026

Nous: An Attempt to Extract and Inject the Cognition Behind Prediction-Market Behavior

arXiv 2606.13038 ↗First posted 11 Jun 2026cs.AIcited by 0

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

Abstract (arXiv)

As LLM agents proliferate in prediction markets and collective decision-making, they risk a cognitive monoculture: agents built on shared foundation models produce correlated forecasts, and recent measurement finds frontier-model errors correlated at r ~ 0.77. We ask whether human cognitive diversity can be recovered from behavior and transferred to LLM agents. Nous extracts a structured eight-dimension behavioral profile from real Polymarket trading activity and injects it into agents through prompts. Our central finding is a dissociation between the two halves of that pipeline. Extraction works, partially: across 100 wallets, 8 of 14 parameters are temporally stable (split-half ICC >= 0.5, bootstrap CI lower bound > 0.3; contrarian score reaches ICC ~ 0.9); wallets are identifiable from their profiles well above chance (top-1 retrieval 17-22% vs. 1% chance); and two of four pre-specified dimensions rank-correlate with future realized profit out-of-sample, though the correlations do not survive behavioral-confound controls. Prompt-level injection does not measurably transmit it: on a semantic embedding metric, structured injection shows no significant advantage over a length-matched control on any model, and the diversity it induces neither reduces ensemble error correlation nor improves Brier score -- a null that persists across exploratory checks on sampling temperature, profile diversity, and question difficulty. Measuring the prompts themselves locates the compression before the model: the structure-to-narrative translator emits near-uniform prompts whose spread does not track profile spread. We position Nous as measuring the cognitive-monoculture problem and the limits of a prompt-level remedy, motivating deeper, below-the-prompt injection (fine-tuning, activation steering). Code, frozen profiles, prompts, and model outputs: https://github.com/WillChienT/nous-paper

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 38 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

21 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026PolySwarm: A Multi-Agent Large Language Model Framework for Prediction Market Trading and Latency Arbitrage4 Apr

Other references · 20

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  5. 2023Role-Play with Large Language Modelscited by 294
  6. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 155
  7. 2024Approaching Human-Level Forecasting with Language Modelscited by 107
  8. 2024Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracycited by 67
  9. 2025TwinMarket: A Scalable Behavioral and Social Simulation for Financial Marketscited by 48
  10. 2024Designing AI-Agents with Personalities: A Psychometric Approachcited by 14
  11. 2026PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Datacited by 12
  12. 2026Prediction Arena: Benchmarking AI Models on Real-World Prediction Marketscited by 10
8 more
  1. 2025Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priorscited by 5
  2. 2026Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agentscited by 5
  3. 2025Prompting for Policy: Forecasting Macroeconomic Scenarios with Synthetic LLM Personascited by 4
  4. 2026The Oracle's Fingerprint: Correlated AI Forecasting Errors and the Limits of Bias Transmissioncited by 3
  5. 2025Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economicscited by 2
  6. 2026Coordination as an Architectural Layer for LLM-Based Multi-Agent Systemscited by 2
  7. 2026Decoding the Human Factor: High Fidelity Behavioral Prediction for Strategic Foresightcited by 1
  8. 2026Multiperspectivity as a Resource for Narrative Similarity Predictioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Can Generative AI agents behave like humans? Evidence from laboratory market experiments
  2. 2026Learning to Simulate Individuals from Macro Social Signals
  3. 2026RetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents
  4. 2026Bridging Expectation Signals: LLM-Based Experiments and a Behavioral Kalman Filter Framework
  5. 2026Competitive Market Behavior of LLMs
  6. 2025Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making
  7. 2026FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards
  8. 2026Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation