FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Muhammad Usman Safder, Ayesha Gull, Rania Elbadry, Fan Zhang, Yankai Chen, Xueqing Peng, Xue, Liu, Preslav Nakov, Zhuohan Xie
• Venue: arXiv: cs.CL
• Published: 2026-06-30
• Collected: 2026-07-01
• URL: http://arxiv.org/abs/2606.31522v1
• PDF: https://arxiv.org/pdf/2606.31522v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers introduce FinPersona-Bench, a simulation benchmark to measure Mandate Salience Decay (MSD) in autonomous financial agents. MSD refers to the gradual loss of behavioral influence of initial mandates over time as market context changes. The study evaluates 18 leading LLMs with different behavioral profiles and finds that MSD compounds over time, affecting different models differently. During crashes, the gap between static and re-grounded agents widens significantly, but the effects of re-grounding are not consistent across all agent types.

What the Document Says

• The study focuses on Large Language Models (LLMs) as autonomous financial agents with initial behavioral mandates.
• Mandate Salience Decay (MSD) is introduced, referring to the gradual loss of behavioral influence of these mandates over time due to changing market contexts.
• FinPersona-Bench is a simulation benchmark that decouples observable price from hidden fundamental value for objective MSD measurement.
• The study evaluates 18 leading LLMs, each with one of three behavioral profiles (conservative, moderate, aggressive).
• MSD compounds over time and varies depending on the model.
• In crash scenarios, the gap between static agents and re-grounded agents grows 4.4x from the first to the final quarter of the simulation.
• The effects of mandate re-grounding are not uniformly positive; it helps conservative agents in low-signal markets but worsens behavior for aggressive agents in the same setting.

Key Concepts Mentioned

• Large Language Models (LLMs)
• Autonomous financial agents
• Mandate Salience Decay (MSD)
• FinPersona-Bench
• Synthetic market
• Behavioral profiles
• Trading without signal
• Panic-selling
• Speculative bubbles
• Static agents
• Mandate re-grounding

Claims Made by the Document

• MSD compounds over time and is model-dependent.
• The gap between static and re-grounded agents grows significantly during crashes.

Evidence Used

• Evaluating 18 leading LLMs shows that MSD compounds over time and is model-dependent.
• In crash scenarios, the behavioral gap between static agents and those receiving periodic mandate re-grounding grows 4.4x from the first to the final quarter of the simulation.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Large Language Models (LLMs) are increasingly deployed as autonomous financial agents initialized with explicit behavioral mandates such as 'preserve capital' or 'avoid speculative bets' that are meant to govern every decision throughout deployment. In practice, however, as market context accumulates over long horizons, these mandates gradually lose their behavioral influence, a phenomenon we formalize as Mandate Salience Decay (MSD). To measure MSD objectively, we introduce FinPersona-Bench, a simulation benchmark in which a synthetic market decouples observable price from hidden fundamental value, enabling falsifiable evaluation across three failure modes: trading without signal in calm markets, panic-selling during crashes, and ignoring fundamental value during speculative bubbles. Evaluating 18 leading frontier and open-source LLMs, each assigned one of three behavioral profiles ranging from strict capital preservation to aggressive growth, shows that MSD compounds over time and is model-dependent. In crash scenarios, the behavioral gap between static agents and those receiving periodic mandate re-grounding grows 4.4x from the first to the final quarter of the simulation. The effects of mandate re-grounding are not uniformly positive: it consistently helps conservative agents in low-signal markets but actively worsens behavior for aggressive agents in the same setting. These findings suggest that reliable long-horizon deployment requires selective, mandate-aware re-grounding based on agent profile and market regime.