cs.RONov 7, 2026

REINS: A Self-Evolving Agent Harness for Real-Time Trajectory Planning

Authors: Zhihong Cui, Hengyu Liu, Haoran Tang, Shijun Liu, Amir Taherkordi, Tor Skeie

Organizations: Department of Informatics, University of Oslo, Norway · Department of Computer Science, Aalborg University, Denmark · Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China · Shandong Key Laboratory of Foundational Software, School of Software, Shandong University, China · 

Abstract

Agent harnesses -- runtime scaffolds that wrap an LLM's reasoning loop with tool dispatch, verification, and persistent memory -- have become the standard substrate for deploying LLMs as autonomous agents, as demonstrated by Claude Code and Codex in software engineering. In trajectory planning, however, this paradigm has not taken hold: existing LLM-based trajectory planning methods either keep the LLM in the decision loop, exceeding the millisecond-level control budget, or offload it to offline rules or training-time supervision -- leaving the runtime planner non-evolving. Intermediate hybrids still lack the verification-and-consolidation loop that makes harnesses reliable. We ask: what runtime harness would let an LLM planner meet real-time constraints while self-evolving into a deployable one? We propose REINS, a harness built on three LLM-planner couplings: LLM outputs are (i) grounded to a learned variable-level dynamics model, (ii) verified via calibrated predicates and forward rollout, and (iii) consolidated into an indexed rule memory that serves future scenes in O(log n) without re-invoking the LLM. The harness closes a self-evolution loop: familiar scenes resolve by memory lookup; novel scenes invoke the LLM, whose verified outputs enrich the memory. Without modifying LLM weights, REINS attains 98%+ compliance, nearly 50% collision reduction, and 1.9-4.6 ms latency on simulated and real-world benchmarks at the tactical decision layer, with LLM invocation rate monotonically declining as memory matures. Code: https://github.com/ZhihongCui/REINS

Figures & tables

Appendix figures & tables25 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution

    Sep 29, 2026Subba Reddy Oota, Francisco Herrera, Jordi Cabot Sagrera +2LLM AgentsLong-Horizon LLM Agents

  2. GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning

    Jul 9, 2026Maureese Williams, Dymitr NowickiTree SearchWorld Model-Based Planning

  3. Harnesses for Inference-Time Alignment over Execution Trajectories

    May 15, 2026Boyuan Wang, Bochao Li, Minghan Wang +2LLM PlanningAgent Harness Optimization