Skip to content
Preprint

EMERGE-Policy: A Robot Mind Emerges Beyond a Single Policy

Aug 2026 · 0 citations · 69 references
Computer Science

TL;DR

These system-level results suggest that through the division of different functional sub-tasks among multiple agents and their concurrent collaboration, as well as the technical paradigm where the model is regarded as a skill and called within the framework, EMERGE-Policy can extend the robust robot policies beyond isolated runs.

Abstract

A robot's effective ``mind''need not reside in a single policy. It can emerge when specialized components perceive, reason, predict, act, verify, and remember within a shared orchestration process. EMERGE-Policy turns this perspective into a graph-structured agentic framework that coordinates both capability invocation and information exchange. A Main Agent retains task-level state within an active context window, while role-specific Sub Agents process perception, execution monitoring, verification, and memory consolidation in isolated contexts and return structured, task-relevant evidence. Role-specific contexts control information load by exposing only decision-relevant evidence to the Main Agent, while the functional Skill interface composes heterogeneous backends as Operational, Imagination, and Evaluation Skills. Criterion-grounded verification, textual failure diagnosis, and Branch Stack recovery provide localized correction, with token-aware external memory preserving task-relevant state. Together, their closed-loop interaction realizes the system-level policy captured by the name EMERGE-Policy. Without additional fine-tuning, we achieved outstanding performance on several public benchmark that have had a wide-reaching impact, and conducted a series of real robot experiments. These system-level results suggest that through the division of different functional sub-tasks among multiple agents and their concurrent collaboration, as well as the technical paradigm where the model is regarded as a skill and called within the framework, EMERGE-Policy can extend the robust robot policies beyond isolated runs.

View source

Similar papers

RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents

RoboFoundry is proposed, the first embodied agentic framework that formulates this process of system-as-policy evolution across foundation models as Self-Evolving System-as-Policy, highlighting its potential for fully autonomous embodied agents.

Jing-Song Liang, Shu-Hao Liao, Shi-Zhe Zhang et al. · 5 citations · ⚡2

Who Holds the Pen? Let Specifications, Not Agents, Sign Off

Experiments on guideline-following and artifact-generation tasks show that specifications can serve not merely as behavioral guidance, but as authority over compliant execution and completion.

Hai-Qing Li, Xin-Yu Ma, Yin-Hao Wu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

CORTEX: A Verified Experience Layer for Generalist Agents

This work introduces CORTEX (Contextual Orchestration and Reuse of Task EXperience), a general AI systems framework that connects specialized agents through an external layer of verified experience and establishes an initial path toward general intelligence through reusable procedures, typed experience, and development...

Garapati Keerthana, Manik Gupta · 0 citations
Preprint Aug 2026

Prime Agent: A Self-Improving RLM Harness

Low-friction, expressive membrane prevents harness failures from becoming model failures and pushes measurement toward the model's true maximal underlying capability, on Factorio, where refinement allows for continuous technology progression and dedicated subagents enable parallelized work.

Seth Karten, Alex L. Zhang, Kevin Thomas et al. · 18 citations · ⚡2
Preprint Sep 2026

RegenHarness: A Robot Agent Harness with Evidence-Gated Recursive Self-Improvement

Long-horizon robot execution requires a clear distinction between a model's proposal, a controller's termination, and verified task completion. We present RegenHarness, an evidence-gated robot-agent harness connecting task planning to heterogeneous robot skills. Its execution architecture couples a model loop for conte...

Kai-Lin Wang, Hao-Xiang Jie, Yao-Yuan Yan et al. · 1 citation
#artificial intelligence Preprint Oct 2026

Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds

Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational policies, tool feedback often conceals hidden side effects under partial observability, and long-horizon tasks require persistent state tracking ac...

Yi-Sen Gao, Yue (Sophie) Guo, Qing Zong et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.