Signal or Noise in Multi-Agent LLM-based Stock Recommendations?

• URL: http://arxiv.org/abs/2604.17327v1
• Date: Sun, 19 Apr 2026 08:43:31 GMT
• Title: Signal or Noise in Multi-Agent LLM-based Stock Recommendations?
• Abstract summary: We present the first portfolio-level validation of MarketSenseAI, a deployed multi-agent LLM equity system.<n>The system routes four specialist agents through a agent that issues a monthly equity thesis and synthesis for each stock in its coverage universe.<n>We ask two questions: do its buy recommendations add value over both passive benchmarks and random selection, and what does the internal agent structure reveal about the source of the edge?
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present the first portfolio-level validation of MarketSenseAI, a deployed multi-agent LLM equity system. All signals are generated live at each observation date, eliminating look-ahead bias. The system routes four specialist agents (News, Fundamentals, Dynamics, and Macro) through a synthesis agent that issues a monthly equity thesis and recommendation for each stock in its coverage universe, and we ask two questions: do its buy recommendations add value over both passive benchmarks and random selection, and what does the internal agent structure reveal about the source of the edge? On the S&P 500 cohort (19 months) the strong-buy equal-weight portfolio earns +2.18%/month against a passive equal-weight benchmark of +1.15% (approximating RSP), a +25.2% compound excess, and ranks at the 99.7th percentile of 10,000 Monte Carlo portfolios (p=0.003). The S&P 100 cohort (35 months) delivers a +30.5% compound excess over EQWL with consistent direction but formal significance not reached, limited by the small average selection of ~10 stocks per month. Non-negative least-squares projection of thesis embeddings onto agent embeddings reveals an adaptive-integration mechanism. Agent contributions rotate with market regime (Fundamentals leads on S&P 500, Macro on S&P 100, Dynamics acts as an episodic momentum signal) and this agent rotation moves in lockstep with both the sector composition of strong-buy selections and identifiable macro-calendar events, three independent views of the same underlying adaptation. The recommendation's cross-sectional Information Coefficient is statistically significant on S&P 500 (ICIR=+0.489, p=0.024). These results suggest that multi-agent LLM equity systems can identify sources of alpha beyond what classical factor models capture, and that the buy signal functions as an effective universe-filter that can sit upstream of any portfolio-construction process.

Related papers

• When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis [66.34225048563418]
  Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alternatives, and decide when to stop.<n>We propose Elo-per-token analysis, which tracks the best solution found at each token budget.<n>We apply it to four general-purpose agents on four open-ended benchmarks, with sessions of up to 100M tokens.
  arXiv  Detail & Related papers  (2026-09-14T09:57:49Z)
• Tabular Deep Learning for Algorithmic Trading: Cross-Regime Bayesian Optimisation for Equity Signal Generation [0.0]
  Five model classes are trained on daily observations from approximately 300 large-cap US equities over eleven years.<n>No individual deep learning architecture outperforms gradient-boosted trees, but combining XGBoost and TabNet using rank aggregation produces a Hybrid ensemble with an annualised return of 51.26%.<n>A near-zero beta indicates this outperformance is driven by stock selection, not market exposure.
  arXiv  Detail & Related papers  (2026-08-27T13:01:32Z)
• PACE: A Proxy for Agentic Capability Evaluation [60.3743414796937]
  We introduce PACE, a framework that constructs proxy benchmarks by selecting instances from existing non-agentic evaluations.<n>Experiments across 14 models, 4 agentic benchmarks, and 19 non-agentic benchmarks show that PACE-Bench predicts agentic scores with leave-one-out cross-validation (LOOCV) mean absolute error (MAE) under 4%, Spearman correlation above 0.80, and pairwise model-ranking accuracy around 85%, all at much less than 1% of the full agentic evaluation cost.
  arXiv  Detail & Related papers  (2026-07-02T10:59:03Z)
• Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems [13.214424787265749]
  We propose a cooperative multi-agent decision system that computes exact Shapley credits across all single, pairwise, and Grand-coalition outputs.<n>Over 1,037 trading days across 13 crypto assets and five seeds, MRC achieves a Sharpe ratio of 1.51 and a cumulative return of 440.1%.
  arXiv  Detail & Related papers  (2026-05-23T09:41:52Z)
• Attributing Emergence in Million-Agent Systems [68.53670424791751]
  Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents.<n>Such studies require attributing macro emergence to individual agents.<n>We adapt Aumann--Shapley path-integral attribution to LLM-powered MAS at million-agent scale.
  arXiv  Detail & Related papers  (2026-05-12T01:49:41Z)
• Designing Agentic AI-Based Screening for Portfolio Investment [1.7499351967216341]
  We introduce a new agentic artificial intelligence (AI) platform for portfolio management.<n>Our architecture consists of three layers. First, two large language model (LLM) agents are assigned specialized tasks.<n>Second, these agents deliberate to generate and agree upon buy and sell signals from a large portfolio, substantially narrowing the pool of candidate assets.
  arXiv  Detail & Related papers  (2026-03-24T15:03:40Z)
• Learning to Aggregate Zero-Shot LLM Agents for Corporate Disclosure Classification [0.0]
  This paper studies whether a lightweight trained aggregator can combine diverse zero-shot large language model judgments into a stronger downstream signal for corporate disclosure classification.<n>I use a sample of 18,420 U.S. corporate disclosures issued by Nasdaq and S&P 500 firms between 2018 and 2024, matched to next-day stock returns.<n>Results show that the trained aggregator outperforms all single agents, majority vote, confidence-weighted voting, and a FinBERT baseline.
  arXiv  Detail & Related papers  (2026-03-21T22:29:19Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Statistical Arbitrage in Polish Equities Market Using Deep Learning Techniques [0.0]
  We study a systematic approach to a popular Statistical Arbitrage technique: Pairs Trading.<n>We replace the second asset with a replication of the first using risk factor representations.<n>We adapt the framework of Avellaneda and Lee (2008) to the Polish market.
  arXiv  Detail & Related papers  (2025-11-20T21:09:34Z)
• Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model [56.92219181993453]
  We propose Reincarnating Mix-policy Proximal Policy Gradient (ReMix) to enable on-policyRFT methods like PPO and GRPO to leverage off-policy data.<n>ReMix consists of three major components: (1) Mix-policy proximal policy gradient with an increased Update-To-Data (UTD) ratio for efficient training; (2) KL-Convex policy constraint to balance the trade-off between stability and flexibility; (3) Policy reincarnation to achieve a seamless transition from efficient early-stage learning to steady improvement.
  arXiv  Detail & Related papers  (2025-07-09T14:29:45Z)
• From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium [52.28048367430481]
  Multi-agent frameworks can boost the reasoning power of large language models (LLMs), but they typically incur heavy computational costs and lack convergence guarantees.<n>We recast multi-LLM coordination as an incomplete-information game and seek a Bayesian Nash equilibrium (BNE)<n>We introduce Efficient Coordination via Nash Equilibrium (ECON), a hierarchical reinforcement-learning paradigm that marries distributed reasoning with centralized final output.
  arXiv  Detail & Related papers  (2025-06-09T23:49:14Z)
• Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis [89.60263788590893]
  Post-training Quantization (PTQ) technique has been extensively adopted for large language models (LLMs) compression.<n>Existing algorithms focus primarily on performance, overlooking the trade-off among model size, performance, and quantization bitwidth.<n>We provide a novel benchmark for LLMs PTQ in this paper.
  arXiv  Detail & Related papers  (2025-02-18T07:35:35Z)
• Automate Strategy Finding with LLM in Quant Investment [32.74265532529821]
  We present a novel three-stage framework leveraging Large Language Models (LLMs) within a risk-aware multi-agent system for automate strategy finding in quantitative finance.<n>Our approach addresses the brittleness of traditional deep learning models in financial applications by: employing prompt-engineered LLMs to generate executable alpha factor candidates across diverse financial data.<n> Experimental results demonstrate the robust performance of the strategy in Chinese & US market regimes compared to established benchmarks.
  arXiv  Detail & Related papers  (2024-09-10T07:42:28Z)

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.