Layered Mutability: Continuity and Governance in Persistent Self-Modifying Agents

• URL: http://arxiv.org/abs/2604.14717v1
• Date: Thu, 16 Apr 2026 07:27:35 GMT
• Title: Layered Mutability: Continuity and Governance in Persistent Self-Modifying Agents
• Abstract summary: This paper introduces layered mutability, a framework for reasoning about that process across five layers.<n>I report a preliminary ratchet experiment in which reverting an agent's visible self-description after memory accumulation fails to restore baseline behavior.<n>The main implication is that the salient failure mode for persistent self-modifying agents is not abrupt misalignment but compositional drift.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior is shaped not only by current prompts but by mutable internal conditions that influence future action. This paper introduces layered mutability, a framework for reasoning about that process across five layers: pretraining, post-training alignment, self-narrative, memory, and weight-level adaptation. The central claim is that governance difficulty rises when mutation is rapid, downstream coupling is strong, reversibility is weak, and observability is low, creating a systematic mismatch between the layers that most affect behavior and the layers humans can most easily inspect. I formalize this intuition with simple drift, governance-load, and hysteresis quantities, connect the framework to recent work on temporal identity in language-model agents, and report a preliminary ratchet experiment in which reverting an agent's visible self-description after memory accumulation fails to restore baseline behavior. In that experiment, the estimated identity hysteresis ratio is 0.68. The main implication is that the salient failure mode for persistent self-modifying agents is not abrupt misalignment but compositional drift: locally reasonable updates that accumulate into a behavioral trajectory that was never explicitly authorized.

Related papers

• Self-Emergence Agent Architecture:Behavior-Inertia HMM, Reflexive Metacognition,and Social-Contrastive Self-Modeling [7.511170831919511]
  Large language model (LLM) agents exhibit strong language-generation and problem-solving capabilities, yet suffer from three structural limitations.<n>Existing generative-agent simulations rely on memory and fixed prompts, maintaining neither behavioral inertia nor endogenous self-reflection.<n>We propose the Self-Emergence Agent Architecture (SEAA), which integrates three components: (i) a Hidden Markov Model (HMM) that encodes long-term behavioral and cognitive inertia as an editable state-transition matrix; (ii) a Reflexion-style verbal metacognition loop whose output updates the HMM parameters themselves; and (iii
  arXiv  Detail & Related papers  (2026-09-15T15:36:10Z)
• Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning [41.371439825328544]
  Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.<n>We develop a layer-wise information-theoretic framework that separates these effects at every depth.<n>Controlled and benchmark experiments confirm the predicted memory scaling, the interior funnel, and the alignment signal's link to forgetting.
  arXiv  Detail & Related papers  (2026-08-12T06:01:49Z)
• 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)
• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• 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)
• Learning Stable Predictors from Weak Supervision under Distribution Shift [2.8410059035029955]
  Learning from weak or proxy supervision is common when ground-truth labels are unavailable.<n>We formalize this as supervision drift, defined as changes in P(y | x, c) across contexts.<n>We study it in CRISPR-Cas13d experiments where guide efficacy is inferred indirectly from RNA-seq responses.
  arXiv  Detail & Related papers  (2026-04-05T23:46:49Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals [0.0]
  We provide an updated characterization of the extent and causes of goal drift.<n>We investigate drift in state-of-the-art models within a simulated stock-trading environment.<n>We find that drift behavior is inconsistent between prompt variations and correlates poorly with instruction hierarchy following behavior.
  arXiv  Detail & Related papers  (2026-03-03T18:50:59Z)
• On the Structural Non-Preservation of Epistemic Behaviour under Policy Transformation [51.56484100374058]
  We formalise such information-conditioned interaction patterns as behavioural dependency.<n>This induces a probe-relative notion of $$-behavioural equivalence and a within-policy behavioural distance.<n>Results identify structural conditions under which probe-conditioned behavioural separation is not preserved under common policy transformations.
  arXiv  Detail & Related papers  (2026-02-24T22:55:21Z)
• Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures [70.48661957773449]
  Emergent Misalignment refers to a failure mode in which fine-tuning large language models on narrowly scoped data induces broadly misaligned behavior.<n>Across multiple domains and model families, we find that fine-tuning models on data exhibiting specific character-level dispositions induces substantially stronger and more transferable misalignment than incorrect-advice fine-tuning.
  arXiv  Detail & Related papers  (2026-01-30T15:28:42Z)
• Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics [0.0]
  Large language model (LLM) agents exhibit abrupt shifts in tone and persona during extended interaction.<n>The role of explicit affective dynamics in shaping long-horizon agent behavior remains underexplored.<n>We introduce an agent-level affective subsystem that maintains a continuous Valence-Arousal-Dominance (VAD) state external to the language model.
  arXiv  Detail & Related papers  (2026-01-22T16:34:05Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Agentic Metacognition: Designing a "Self-Aware" Low-Code Agent for Failure Prediction and Human Handoff [0.0]
  Non-deterministic nature of autonomous agents presents reliability challenges.<n> secondary, "metacognitive" layer actively monitors primary LCNC agent.<n>Inspired by human introspection, this layer is designed to predict impending task failures.
  arXiv  Detail & Related papers  (2025-09-24T06:10:23Z)

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.