Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.33123

Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring

Zhixiang Zhang·Zesen Liu·Wai Ip Lai·Hongxu chen·Dongdong She
View original source ↗Read source document ↗Export metadata ↓

Abstract

Self-evolving agent harnesses continually update persistent components such as memory, prompts, skills, and tools. We call this process harness evolution. However, such evolution could introduce unexpected safety risks. Existing work studies harness misevolution and validates candidate harnesses or attributed individual component updates, leaving safety analysis of cross-component update interactions largely unexamined. To address this gap, we study compositional safety failures in harness evolution, where interactions among individually safe and utility-preserving component updates can produce undesirable or unsafe agent behavior, revealing a safety risk intrinsic to harness evolution. Across three safety-related benchmarks, we identify 43 pairwise and 18 irreducible 3-way compositional safety failures. Conventional solution incurs combinatorial complexity in validating cross-component interactions, leaving the safety checking impractical as the harness evolves. To solve this, we introduced a typed hypergraph that represents component states as nodes and safety-relevant higher-order interactions as hyperedges. When the harness changes, the hypergraph updates only the interaction neighborhood of the changed states rather than reconstructing the global composition space. Building on that, we develop a hypergraph-guided runtime monitoring mechanism. Experiments show that our method effectively mitigates compositional safety risks while preserving task utility and reducing interaction-checking costs, and further reveal an empirical safety-utility-cost trade-off across different safety mechanisms.

Explore related subjects

cs.AIcs.SE

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Zhixiang Zhang, Zesen Liu, Wai Ip Lai, Hongxu chen, Dongdong She. 2026-09-27. Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring. https://arxiv.org/abs/2609.33123

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

FlexQuant: Elastic Quantization Framework for Locally Hosted LLM on Edge Devices

Deploying LLMs on edge devices presents serious technical challenges. Memory elasticity is crucial for edge devices with unified memory, where memory is shared and fluctuates dynamically. Existing solutions suffer from either poor transition granularity or high storage costs. We propose FlexQuant, a novel elasticity framework that generates an ensemble of quantized models, providing an elastic hosting solution with 31x more deployment options, 15x granularity improvement, and 10x storage reduction compared to SoTA methods. FlexQuant works with most quantization methods and creates a family of trade-off options under various storage limits through our pruning method. It brings great performance and flexibility to the edge deployment of LLMs.

cs.AI↗
arXiv2026

Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty

Real-world decision-making often involves uncertainty expressed in linguistic rather than numerical terms, and Prospect Theory (PT) provides a classic framework for modeling human behavior under such uncertainty. Although recent studies have developed frameworks to estimate PT parameters for Large Language Models (LLMs), few have examined whether PT itself adequately describes LLM decision-making behavior. To address these gaps, we develop a streamlined workflow grounded in a classic behavioral economics experimental paradigm. First, we estimate PT parameters and evaluate how well the resulting model captures LLM decision-making behavior. We then derive probability mappings for epistemic markers in the same context and inject them into prompts to examine the stability of PT parameters under linguistic uncertainty. Our findings suggest that PT does not consistently provide a reliable account of LLM decision-making across models, and that its application to LLMs is likely sensitive to epistemic uncertainty. The findings caution against the deployment of PT-based frameworks in real-world applications where epistemic ambiguity is prevalent, giving valuable insights in behaviour interpretation and future alignment direction for LLM decision-making.

cs.AI↗
arXiv2026

Enabling Regulatory Multi-Agent Collaboration: Architecture, Challenges, and Solutions

Large language models (LLMs)-empowered autonomous agents are transforming both digital and physical environments by enabling adaptive, multi-agent collaboration. While these agents offer significant opportunities across domains such as finance, healthcare, and smart manufacturing, their unpredictable behaviors and heterogeneous capabilities pose substantial governance and accountability challenges. In this paper, we propose a blockchain-enabled layered architecture for regulatory agent collaboration, comprising an agent layer, an off-chain computation layer, and an on-chain anchoring layer. Within this framework, we design three key modules: (i) an agent behavior tracing and arbitration module for automated accountability, (ii) a dynamic reputation evaluation module for trust assessment in collaborative scenarios, and (iii) a malicious behavior forecasting module for early detection of adversarial activities. Our approach establishes a systematic foundation for trustworthy, resilient, and scalable regulatory mechanisms in large-scale agent ecosystems. Finally, we discuss the future research directions for blockchain-enabled regulatory frameworks in multi-agent systems.

cs.AI↗