Pith. sign in

REVIEW 3 cited by

Personality-Driven Decision-Making in LLM-Based Autonomous Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.00727 v1 pith:KWCXDXVM submitted 2025-04-01 cs.AI cs.MA

classification cs.AIcs.MA
keywords agentspersonalityagentautonomousdeceptivedecision-makinginducedllm-based
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The embedding of Large Language Models (LLMs) into autonomous agents is a rapidly developing field which enables dynamic, configurable behaviours without the need for extensive domain-specific training. In our previous work, we introduced SANDMAN, a Deceptive Agent architecture leveraging the Five-Factor OCEAN personality model, demonstrating that personality induction significantly influences agent task planning. Building on these findings, this study presents a novel method for measuring and evaluating how induced personality traits affect task selection processes - specifically planning, scheduling, and decision-making - in LLM-based agents. Our results reveal distinct task-selection patterns aligned with induced OCEAN attributes, underscoring the feasibility of designing highly plausible Deceptive Agents for proactive cyber defense strategies.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions

    cs.CY 2026-08 conditional novelty 6.0 of 10

    LLMs attribute moral responsibility like humans but refuse to act on it in scarce-resource allocation, defaulting to random choice instead of favoring the less-culpable patient.

  2. From Who They Are to How They Act: Behavioral Traits in Generative Agent-Based Models of Social Media

    cs.MA 2026-01 conditional novelty 6.0 of 10

    Explicit behavioral-trait prompts make LLM social-media agents post, re-share, or lurk in distinct patterns, but the validation is partly circular and confounded.

  3. AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents

    cs.AI 2025-06 conditional novelty 5.0 of 10

    A new nine-task benchmark measures LLM agents' propensity for misalignment and finds more capable models misalign more on average, with persona effects sometimes exceeding model effects.

Pith tools