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

Kailin Wang; Haoxiang Jie; Yaoyuan Yan; Zhiyou Heng; Zhaosong Li

cs.ROSep 23, 2026

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

Authors: Kailin Wang, Haoxiang Jie, Yaoyuan Yan, Zhiyou Heng, Zhaosong Li

Organizations: AI Lab, Country Garden Services Group

Abstract

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 context-conditioned proposals with an agent loop for dispatch, observation, verification, commitment, and bounded recovery. Four role-isolated contexts separate planning, supervision, verification, and recovery inputs. Versioned memory distinguishes observed facts from accepted task progress, while an identity- and version-bound commit gate controls updates to trusted task state. The runtime combines duplicate-dispatch control, resource leases, and recovery budgets under explicit backend contracts, and checks the original user goal before reporting completion. To our knowledge, we are the first to introduce an evidence-gated recursive self-improvement (RSI) protocol for embodied robotic agents. Across missions, execution records motivate candidate changes to context rules, task templates, routing, and recovery policies; fixed regression checks and release authorization govern their acceptance; versioned rollout and rollback preserve configuration traceability. This RSI protocol revises the harness configuration without online model-weight updates or permission to weaken the commit gate. A real quadruped deployment documents voice-triggered warehouse navigation, panoramic inspection, visual analysis, message delivery, return, and spoken reporting through linked audio, images, trajectories, and receipts. A separate circuit demonstrates why completion depends on execution history rather than endpoint proximity alone. Together, the cases demonstrate integrated perception, physical execution, communication, and history-dependent completion in real-world robot tasks.

Figures & tables

Figure 1: RegenHarness architecture and execution authority. Versioned memory supplies role-isolated contexts for planning (C1), supervision (C2), verification (C3), and recovery (C4). Only the identity- and version-bound commit gate accepts task progress. Blue paths carry execution and context; green paths carry accepted progress; amber paths denote bounded recovery. Interchangeable providers remain outside task-state commit authority.

View	Consumer	Primary question
C1	Planner	What should happen next?
C2	Skill	How should this node be executed?
C3	Verifier	Did the intended effect occur?
C4	Recovery	What bounded response is justified?

Table 1: Role-isolated contexts compiled from one versioned state.

Figure 2: Step-by-step evidence from one real voice-triggered warehouse inspection. The waveform is derived from the original microphone recording; the photographs are unaltered full frames from the destination panorama. English text translates or summarizes the saved command and report. Arrival distances are supervisor-reported; communication outcomes are system-side receipts. Each panel summarizes the corresponding recorded stage.

Figure 3: VLM + omni_planner : exploration architecture and field mapping output. (a) The architecture assigns exploration-goal selection to the VLM, local motion generation to omni_planner , and map updates to SLAM, with RegenHarness supervising execution. (b) The saved point cloud and recorded SLAM trajectory, aligned using recorded transforms. The two panels connect the exploration workflow to the site’s mapped geometry and robot trajectory.

Figure 4: Site geometry and configured task semantics. (a) Task area and reference routes. (b) Full recorded map extent. (c) Place-to-target bindings: A is departure/return; B is office_storage . These sparse anchors provide configured mission-level semantics over the recorded geometric map.

Figure 5: Navigation legs of the recorded voice-triggered warehouse mission. (a) Reference and body trajectories from A to B and back. (b) Distance to each segment’s goal relative to reference dispatch; the dotted line is the 0.40 m tolerance. Traces continue to the end of recording; Table 6.5 reports the supervisor’s arrival distances and the distances at the last recorded poses.

Execution segment	Commanded route and target	Reference path length $L_{\mathrm{ref}}$ (m)	Goal distance at arrival declaration (m)	Goal distance at last recorded pose (m)
Outbound	A $\rightarrow$ B; target B	17.62	0.11	0.09
Return	B $\rightarrow$ A; target A	17.62	0.17	0.17
Circuit	A $\rightarrow$ circuit $\rightarrow$ A	18.83	0.25	0.15

Table 2: Per-segment navigation measurements. Outbound and return are the two legs of the voice-triggered warehouse inspection; the circuit is a separate mission. A is the departure/return anchor and B the configured storage-area target in Figure 6.4 . All numeric distances are in meters.

Figure 6: Circuit completion requires execution history. (a) Reference and body trajectory with camera locations c–e. (b) The robot starts within the arrival tolerance, leaves, and returns. (c–e) Original onboard frames from that recording. Departure, trajectory, and return records establish the navigation-level completion sequence.

Long-Horizon Agent Tasks

Long-Horizon Agent Tasks study how AI agents plan, remember, and act reliably across extended, multi-step interactions.

See all 195 papers

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents
Sep 30, 2026Haoyuan Deng, Jiebin Liu, Tengxiao Zhang +3Long-Horizon Robotic Manipulation Continual Robot Learning
Nanyang Technological University · Nanjing University
Harness Self-Evolution for Long-Horizon Terminal Agents
Oct 20, 2026Ruhan Wang, Yucheng Shi, Zongxia Li +6Agent Harness Optimization LLM Agent Reliability
Tencent HY LLM Frontier · Indiana University · University of Maryland, College Park +2
FastHarness: Experience-Driven Review Scheduling for Vision-Language-Action Policies
Oct 22, 2026Tao Lin, Yuxin Du, Haoxiao Wang +2Agentic AI for Robotics Agent Harness Optimization
School of AI, Shanghai Jiao Tong University · Zhejiang University

Sep 30, 2026J/K move · Enter open · S save

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

Haoyuan Deng, Jiebin Liu, Tengxiao Zhang, Langning Yan+2

Nanyang Technological University · Nanjing University

Long-Horizon Robotic Manipulation Continual Robot Learning Language-Conditioned Robot Manipulation Agent Harness Optimization

Open paper AskPDF arXiv

Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on which system component should be revised. We propose DynaHarness, a dynamic physical harness that couples semantic reasoning with physical governance through a shared execution contract and turns failure evidence into validated capability revisions. To be more specific, the slow brain proposes capabilities and symbolic arguments, while the fast brain grounds and monitors commands, refuses unresolved actions, substitutes capabilities, and requests replans when needed. The physical execution contract bounds each accepted command and records execution evidence across analytic skills, recovery skills, and the frozen VLA. Failure attribution localizes faults in these records and directs targeted revisions of reusable capabilities or execution mechanisms. Paired regression checks govern admission or rejection, closing the self-evolution loop. On LIBERO-Pro, DynaHarness achieves 75.2% on 800 newly sampled initial states, compared with 17.5% for the frozen policy. With the same capability library, full dynamic execution reaches 74.0% versus 63.9% under nominal one-step replanning. This demonstrates the value of DynaHarness as a dynamic physical harness that governs how existing capabilities are grounded, monitored, and coordinated during execution. Our project page is at https://denghaoyuan123.github.io/Dynaharness_page/.

Abstract

Long-Horizon Agent Tasks

Explore similar work

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

Harness Self-Evolution for Long-Horizon Terminal Agents

FastHarness: Experience-Driven Review Scheduling for Vision-Language-Action Policies