RouterVLA: Turning Smoke Tests into Supervision for Heterogeneous VLA Selection

• URL: http://arxiv.org/abs/2606.27355v1
• Date: Thu, 25 Jun 2026 17:56:33 GMT
• Title: RouterVLA: Turning Smoke Tests into Supervision for Heterogeneous VLA Selection
• Abstract summary: We study whether pre-deployment evaluation rollouts can be reused to supervise policy selection.<n>We find that pre-deployment evaluation rollouts can be reused to supervise policy selection.
• Score: 5.188057876794867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study whether pre-deployment evaluation rollouts can be reused to supervise policy selection. Robot teams routinely smoke test candidate vision-language-action (VLA) policies, then compress those trials into a global winner. RouterVLA evaluates this idea with outcome-disjoint cross-fitting: recorded probes build a profile for each frozen expert, and a separate trial scores the selected expert without entering its profile. Across 34,752 LIBERO-Plus rollout records, a transparent probe-success rule raises held-out success from 0.4686 to 0.6149, a +14.64pp gain. Under the scalar-only profiles studied here, learned scorers are statistically indistinguishable from this rule, showing that commissioning carries the routing value while extra scalar scorer capacity does not create it. Reusing the scored trial inflates the measured gain by $1.87\times$, so credible ledger routing needs outcome separation; model scaling improves individual policies, while commissioning-aware routing improves the system built from them.

Related papers

• On-Policy Self-Distillation in Diffusion Models [89.32656931795293]
  Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change.<n>We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries.<n>Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators.
  arXiv  Detail & Related papers  (2026-08-25T14:55:24Z)
• Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents [60.650808962786364]
  We study whether native MoE router traces can guide steering and selection without an external judge or selection-time test execution.<n>Our analysis shows that routing provides a robust behavioral role signal; token-granular readouts and decision-matched comparison sets turn it into effective control.<n>We evaluate on SWE-bench Verified using open-weight sparse MoE agents across scales and reasoning-effort settings.
  arXiv  Detail & Related papers  (2026-08-23T03:07:03Z)
• Reuse Before You Retrieve: Diagnosing Headroom and Complementarity for Test-Time Augmentation of Embodied Multimodal Policies [56.86456077356948]
  Frozen-language-action (VLA) policies are increasingly improved at test time.<n>Additional sampling is useful only when better behavior already exists within the policy's rollouts.<n>Retrieval is most useful when the relevant action prior is not reliably represented by the policy.
  arXiv  Detail & Related papers  (2026-08-18T08:11:31Z)
• When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models [4.8190992438931035]
  LearnStop is a hidden-state-free logistic stopper over prefix-observable features.<n>A trajectory decomposition predicts the regime: learning pays where answers oscillate and correctness evidence is spread.<n>Cost accounting sharpens the picture further -- the same policy that saves 32% of tokens under KV-cache forking costs 121% extra under black-box repeated prefilling.
  arXiv  Detail & Related papers  (2026-06-29T19:33:42Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents [48.80766702702854]
  LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised.<n>This signal degenerates on outcome-homogeneous groups where all sampled trajectories share the same correctness, yielding zero within-group advantage and no gradient.<n>We propose ARBOR (Adaptive Buffer for Online Reward), a reusable process-reward framework that maintains a rubric memory shared across queries.
  arXiv  Detail & Related papers  (2026-06-02T06:58:54Z)
• What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs [52.50210189669399]
  Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs)<n>We propose SliceScorer, a deterministic scoring rule for missing-slice recommendation.<n>We show that SliceNav surfaces high-risk coverage gaps more effectively than prior slice-discovery methods.
  arXiv  Detail & Related papers  (2026-06-01T03:18:01Z)
• What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies [36.91260665881213]
  Vision-language--action (VLA) policies are trained to imitate actions; their loss never asks them to estimate reward, progress, or future success.<n>We recover Monte-Carlo outcome targets using lightweight linear probes on frozen features.<n>The gains are not universal and require additional inference compute, but the underlying finding is clean.
  arXiv  Detail & Related papers  (2026-05-27T14:23:29Z)
• RECTOR: Priority-Aware Rule-Based Reranking for Compliance-Aware Autonomous Driving Trajectory Selection [0.8363171780853939]
  We present textscRECTOR (Rule-Enforced Constrained Trajectory Orchestrator)<n>It scores candidates against a tiered rulebook via differentiable proxies and a scene-conditioned applicability mechanism.<n>It selects with a deterministic $varepsilon$-lexicographic rule that preserves cross-tier priority -- without retraining the predictor.
  arXiv  Detail & Related papers  (2026-05-24T14:17:00Z)
• Step-wise Rubric Rewards for LLM Reasoning [72.17879367869503]
  Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models.<n>We find 18.2% of steps in correct responses are wrong yet positively rewarded.<n>Across six mathematical reasoning benchmarks, SRaR improves average accuracy over RaR by 3.57 points.
  arXiv  Detail & Related papers  (2026-05-17T07:08:14Z)
• Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes [24.516406575400016]
  We study auto research as a closed empirical loop driven by external measurement.<n>Each submitted trial carries a hypothesis, an executable code edit, an evaluator-owned outcome, and feedback that shapes the next proposal.<n>We instantiate this loop with specialist agents that partition recipe surfaces and share measured lineage across trials.
  arXiv  Detail & Related papers  (2026-05-07T06:13:43Z)
• Conservative Offline Robot Policy Learning via Posterior-Transition Reweighting [36.23660195981511]
  Posterior-Transition Reweighting (PTR) is a reward-free and conservative post-training method.<n>It decides how much each training sample should influence the supervised update.<n>PTR reallocates credit according to how attributable each sample's post-action consequence is under the current representation.
  arXiv  Detail & Related papers  (2026-03-17T14:05:35Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.