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

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.
ViewConsumerPrimary question
C1PlannerWhat should happen next?
C2SkillHow should this node be executed?
C3VerifierDid the intended effect occur?
C4RecoveryWhat 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 segmentCommanded route and targetReference path length LrefL_{\mathrm{ref}} (m)Goal distance at arrival declaration (m)Goal distance at last recorded pose (m)
OutboundA →\rightarrow B; target B17.620.110.09
ReturnB →\rightarrow A; target A17.620.170.17
CircuitA →\rightarrow circuit →\rightarrow A18.830.250.15
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.
More in this topic

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

Explore similar work

CardsList
Sep 30, 2026

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

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/.

Haoyuan Deng, Jiebin Liu, Tengxiao Zhang +3

Nanyang Technological University · Nanjing University

Long-Horizon Robotic ManipulationContinual Robot LearningLanguage-Conditioned Robot ManipulationAgent Harness Optimization
AskPDF
Oct 20, 2026

Harness Self-Evolution for Long-Horizon Terminal Agents

Long-horizon terminal agents may solve a task in one run yet fail across repeated runs. Stochastic errors can propagate through actions and context, creating a gap between capability and reliable execution. We present RiseHarness, a framework for iteratively improving agent harnesses with model weights fixed. It focuses on flipping tasks with both successful and failed runs under the same configuration, using successful runs as references for failure analysis. RiseHarness combines agent trajectories with internal harness traces from a runtime monitor to examine how model actions interact with command execution, feedback, context management, and completion decisions. A Harness Handbook links this evidence to harness behaviors and source code, helping identify recurring problems in mechanisms shared across tasks. RiseHarness then searches other harness frameworks for relevant implementations and adapts them as design references to the current model and execution protocol. Candidate changes undergo behavioral checks and repeated task evaluation; versions with measured gains seed the next iteration. This loop integrates suitable mechanisms from different frameworks into a single harness and uses new execution evidence to guide further changes. We evaluate task success and reliability across models, ablate harness execution evidence and external research, and test transfer to unseen benchmarks with the same model. RiseHarness treats a specific model as the unit of harness adaptation, studying how changes to shared interaction mechanisms can make existing capabilities more reliable across tasks.

Ruhan Wang, Yucheng Shi, Zongxia Li +6

Tencent HY LLM Frontier · Indiana University · University of Maryland, College Park +2

Agent Harness OptimizationLLM Agent ReliabilityLong-Horizon LLM AgentsProcess-Based Agent Evaluation
AskPDF
Oct 22, 2026

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

Agentic robot systems combine language-model reasoning with robot policies to monitor execution and recover from failures. However, reviewing every action chunk incurs substantial overhead, even in familiar situations. We introduce FastHarness, an experience-driven execution harness that adaptively schedules GPT-6 Astra supervision of a π0.5 policy. A fast path uses stage memory and reviewed outcomes to reduce review frequency as experience accumulates, while a complementary recovery path focuses supervision on correcting errors. Once recovery is verified, routine execution resumes, with failure experience retained to guide future interventions. The policy remains frozen and generates fresh actions from current observations. Across four simulated manipulation tasks, reviewer token use decreases by an average of 57.2% per task from the first evaluated episode to the mean of the final five episodes. Mean episode time decreases from 85.5 to 52.0 minutes over the same interval. On the same tasks, mean success increases from 80% for GPT-as-Policy (π0.5 + GPT-6 Astra) to 97.19% with FastHarness. These results highlight adaptive supervision as a practical route to more efficient agentic robotics without additional model training.

Tao Lin, Yuxin Du, Haoxiao Wang +2

School of AI, Shanghai Jiao Tong University · Zhejiang University

Agentic AI for RoboticsAgent Harness OptimizationVLMs for Robotics
AskPDF