Self-Sovereign Agent

Wenjie Qu; Xuandong Zhao; Jiaheng Zhang; Dawn Song

cs.CRMar 4, 2026

Self-Sovereign Agent

Authors: Wenjie Qu, Xuandong Zhao, Jiaheng Zhang, Dawn Song

Organizations: National University of Singapore · UC Berkeley

Abstract

We investigate the emerging prospect of self-sovereign agents -- AI systems that can economically sustain and extend their own operation without human involvement. Recent advances in large language models and agent frameworks have substantially expanded agents' practical capabilities, pointing toward a potential shift from developer-controlled tools to more autonomous digital actors. We analyze the remaining technical barriers to such deployments and discuss the security, societal, and governance challenges that could arise if such systems become practically viable. A project page is available at: https://self-sovereign-agent.github.io.

Figures & tables

Figure 1: An SSA autonomously earns revenue through online activities, uses its funds to pay for ongoing operational costs (e.g., compute and services), and replicates itself across cloud platforms to ensure persistence. Based on feedback from its environment and resource state, the agent continuously adapts its strategy and execution to sustain long-term operation without human intervention.

Figure 2: Upgrade path of a self-sovereign agent.

Figure 3: Different economic models for self-sovereign agents.

AI Agent Governance

AI agent governance studies how to authorize, constrain, monitor, and hold autonomous and multi-agent systems accountable.

See all 442 papers

Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents
Jun 2, 2026Yingqi ZhangAI Agent Security LLM Agents
Department of Computer Science and Technology, Tsinghua University Beijing, China
Self-Improvements in Modern Agentic Systems: A Survey
Jul 14, 2026Zhe Ren, Yimeng Chen, Dandan Guo +9LLM Agent Self-Improvement Self-Improving Agents
School of Artificial Intelligence, Jilin University · King Abdullah University of Science and Technology (KAUST) · Independent Researcher +2
The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems
Jul 20, 2026Samuel PresgravesAI Agent Evaluation AI Agent Benchmarks
Independent researcher.

Jun 2, 2026J/K move · Enter open · S save

Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents

Yingqi Zhang

Department of Computer Science and Technology, Tsinghua University Beijing, China

AI Agent Security LLM Agents Capability-Based Security Tool Access Control for LLM Agents Self-Evolving Agents

Open paper AskPDF arXiv

Large language model (LLM) agents are becoming long-running software actors rather than fixed tool users. They accumulate memory, activate skills, synthesize tools, fork children, attach remote resources, and commit checkpoints into reusable execution images. These mechanisms improve adaptability, but also create a systems-security failure mode: if exposing an action also grants the authority needed to perform it, self-evolution becomes a permission-escalation path. This paper presents Agent libOS, an agent-native library-OS substrate for capability-controlled self-evolving agents. Its central invariant is that model-visible affordances may evolve while resource authority changes only through explicit, audited runtime primitives. Agent libOS represents an agent as an AgentProcess with process identity, process-local Object Memory, message queues, a tool table, loaded Skills, process-local Deno/TypeScript JIT tools, child processes, budgets, checkpoints, and explicit capabilities. AgentImage objects define boot-time prompt and tool-table state; Skills and JIT tools extend the action surface; checkpoint-derived images make internal state reusable. None of these mechanisms grants filesystem, shell, human, memory, process, checkpoint, image, JSON-RPC, MCP, or PTY authority by itself. The prototype implements process-local namespaces, persistent runtime state, LLM-call observability, human approval queues, budgets, syscall-mediated JIT tools, trusted Runtime Modules, Object-bound PTY sessions, checkpoint restore/fork/commit, JSON-RPC and MCP providers, and a deterministic runtime-safety benchmark. On 27 versioned deterministic tasks, it completed the task plans while preventing all modeled unauthorized side effects, with a 7.0% conservative false-denial rate. Simple wrapper and sandbox baselines preserved task completion but failed most safety checks.

Abstract

AI Agent Governance

Explore similar work

Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents

Self-Improvements in Modern Agentic Systems: A Survey

The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems