Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents

• URL: http://arxiv.org/abs/2605.28850v1
• Date: Sat, 16 May 2026 16:53:34 GMT
• Title: Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents
• Abstract summary: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments.<n>We find that planning embeddings drift from normal-state centroids, fused plan-risk representations separate normal from pre-drawdown states, and diagnostics show effective-rank contraction before failures.<n>We also find that structured risk feedback can act as an external alignment signal without fine-tuning, but not as a universal performance enhancer.
• Score: 0.0635655952373977
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. Using TradeArena, an auditable trading-agent testbed with risk reports, execution simulation, memory, and replayable trajectories, we analyze how rationales, positions, and interventions evolve under market stress. We find measurable pre-failure signatures: planning embeddings drift from normal-state centroids, fused plan-risk representations separate normal from pre-drawdown states, and manifold diagnostics show effective-rank contraction before failures. To address small-sample and embedding-choice concerns, we use 80 rolling failure anchors across eight LLM trajectories and show that contraction persists across hash, LSA, Transformer, and white-box hidden-state probes. Stress tests with CoT-free target weights, lexical controls, OHLCV noise, and false-audit reports indicate that rationale-level contraction can vanish without rationales, while intent-space contraction may remain; lexical diversity does not collapse; and fused signatures remain informative under noise. We also find that structured risk feedback can act as an external alignment signal without fine-tuning, but not as a universal performance enhancer: true audit feedback improves calibration for some models, return and drawdown for others, and reveals cases where hidden or placebo feedback has higher short-horizon return but weaker alignment diagnostics. Finally, a 51-stock intraday experiment reveals a correlation blind spot: LLM rationales often justify concentrated exposure to coupled assets that the risk layer repeatedly clips, with a rolling Markowitz baseline as a covariance reference. These results support a research claim rather than a profitability claim: auditable risk feedback and representation trajectories reveal when LLM financial reasoning is aligning, drifting, or failing.

Related papers

• Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique [1.1172382217477128]
  Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures.<n>Existing detection methods fail to provide actionable, real-time correction as they either do not localize the hallucinations, or incur prohibitive inference latency.<n>We introduce the Latent Critic, a lightweight low-rank adapter (LoRA) that operates concurrently with a frozen base LLM's generation.
  arXiv  Detail & Related papers  (2026-08-11T03:26:16Z)
• The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence [23.772113719172896]
  Report headline Sharpe ratios from end-to-end LLM trading agents should not be treated as deployment evidence.<n>Report robustness is not tradable probability, narrative reasoning is not numerical execution, and model priors may become undisclosed implicit factor exposures.
  arXiv  Detail & Related papers  (2026-05-16T09:14:35Z)
• Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation [19.888565537472363]
  CoRM-RAG (Counterfactual Risk Minimization for RAG) is a framework that aligns retrieval with decision safety rather than mere similarity.<n>We introduce a Cognitive Perturbation Protocol to simulate user biases during training, which is then distilled into a lightweight Evidence Critic.<n>This scoring module learns to identify documents that possess sufficient evidential strength to steer the model toward correctness despite adversarial query perturbations.
  arXiv  Detail & Related papers  (2026-05-02T07:22:24Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks [19.272001035427987]
  We propose an explainable AML triage framework that treats triage as an evidence-constrained decision process.<n>Our method combines (i) retrieval-augmented evidence bundling from policy/typology guidance, customer context, alert triggers, and transaction subgraphs, (ii) a structured LLM output contract that requires explicit citations and separates supporting from contradicting or missing evidence, and (iii) counterfactual checks that validate whether minimal, plausible perturbations lead to coherent changes in both the triage recommendation and its rationale.
  arXiv  Detail & Related papers  (2026-03-22T05:51:40Z)
• Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination [60.197429875410286]
  Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems.<n>Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion.<n>In vision, masking highly coupled components improves robustness without costly adversarial training.<n>In language, the same prefill-stage probe detects hallucination risk before generating any answer tokens.
  arXiv  Detail & Related papers  (2026-03-20T02:07:10Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• DRIFT: Detecting Representational Inconsistencies for Factual Truthfulness [5.785021425715989]
  LLMs often produce fluent but incorrect answers, yet detecting such hallucinations typically requires multiple sampling passes or post-hoc verification.<n>We propose a lightweight probe to read these signals directly from hidden states.<n>We develop an LLM router that answers confident queries immediately while delegating uncertain ones to stronger models.
  arXiv  Detail & Related papers  (2026-01-20T18:16:10Z)
• Decision-Aware Trust Signal Alignment for SOC Alert Triage [0.0]
  The present paper presents a decision-sensitive trust signal correspondence scheme of SOC alert triage.<n>The framework combines confidence that has been calibrated, lightweight uncertainty cues, and cost-sensitive decision thresholds into coherent decision-support layer.<n>We show that false negatives are greatly amplified by the presence of misaligned displays of confidence, whereas cost weighted loss decreases by orders of magnitude between models with decision aligned trust signals.
  arXiv  Detail & Related papers  (2026-01-08T01:41:54Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them [52.764019220214344]
  Hallucinations pose critical risks for large language model (LLM)-based agents.<n>We present MIRAGE-Bench, the first unified benchmark for eliciting and evaluating hallucinations in interactive environments.
  arXiv  Detail & Related papers  (2025-07-28T17:38:29Z)

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.