Skip to content
← Back to explorer

BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format

Roland Pihlakas, Sruthi Susan Kuriakose · Sep 2, 2025 · Citations: 0

Abstract

Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specification gaming) at the expense of everything else. LLM-based systems are often assumed to be safer because they function as next-token predictors rather than persistent optimisers. In this work, we empirically test this assumption by placing LLMs in simple, long-horizon control-style environments that require maintaining state of or balancing objectives over time: sustainability of a renewable resource, single- and multi-objective homeostasis, and balancing unbounded objectives with diminishing returns. We find that, although models frequently behave appropriately for many steps and clearly understand the stated objectives, they often lose context in structured ways and drift into runaway behaviours: ignoring homeostatic targets, collapsing from multi-objective trade-offs into single-objective maximisation - thus failing to respect concave utility structures. These failures emerge reliably after initial periods of competent behaviour and exhibit characteristic patterns (including self-imitative oscillations, unbounded maximisation, and reverting to single-objective optimisation). The problem is not that the LLMs just lose context or become incoherent - the failures systematically resemble runaway optimisers. Our results suggest that long-horizon, multi-objective misalignment is a genuine and under-evaluated failure mode in LLM agents, even in extremely simple settings with transparent and explicitly multi-objective feedback. Although LLMs appear multi-objective and bounded on the surface, their behaviour under sustained interaction, particularly involving multiple objectives, resembles brittle, poorly aligned optimisers whose effective objective gradually shifts toward unbounded and single-metric maximisation.

HFEPX Relevance Assessment

This paper has direct human-feedback and/or evaluation protocol signal and is likely useful for eval pipeline design.

Eval-Fit Score

12/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

High-confidence candidate

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: General
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Simulation Env
  • Agentic eval: Long Horizon
  • Quality controls: Not reported
  • Confidence: 0.40
  • Flags: ambiguous

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Deterministic synthesis

Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specification gaming) at the expense of everything else. HFEPX signals include Simulation Env, Long Horizon with confidence 0.40. Updated from current HFEPX corpus.

Generated Mar 3, 2026, 7:11 PM · Grounded in abstract + metadata only

Key Takeaways

  • Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser",…
  • LLM-based systems are often assumed to be safer because they function as next-token predictors rather than persistent optimisers.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Verify metric definitions before comparing against your eval pipeline.

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specification gaming) at the expense of everything else.
  • LLM-based systems are often assumed to be safer because they function as next-token predictors rather than persistent optimisers.
  • In this work, we empirically test this assumption by placing LLMs in simple, long-horizon control-style environments that require maintaining state of or balancing objectives over time: sustainability of a renewable resource, single- and mu

Why It Matters For Eval

  • Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.g., "paperclip maximiser", specification gaming) at the expense of everything else.
  • Our results suggest that long-horizon, multi-objective misalignment is a genuine and under-evaluated failure mode in LLM agents, even in extremely simple settings with transparent and explicitly multi-objective feedback.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Simulation Env

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Gap: Metric reporting is present

    No metric terms extracted.

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.