Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration

• URL: http://arxiv.org/abs/2606.00145v1
• Date: Fri, 29 May 2026 02:48:13 GMT
• Title: Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration
• Abstract summary: We study completion under a deployable low-calibration regime motivated by open-ended instruction spaces.<n>We propose Completion at the Boundary, which predicts an event-local completion object in the form of Boundary-Phase Tokens.<n>We show that CaB improves composite execution and handoff quality on a first-person Minecraft VLA benchmark under matched capacity and deployability constraints.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language-action (VLA) agents can execute natural-language instructions, yet deployed systems still lack an operational interface: deciding when the instruction is complete. This gap is acute in short composites ("do A, then B"), where mistimed handoffs cascade into downstream failures. Completion is inherently closed-loop because switching is an intervention that changes the instruction context and thus future actions and observations. We study completion under a deployable low-calibration regime motivated by open-ended instruction spaces, enforcing no test-time relearning and a single globally calibrated switching rule selected once on development set and reused unchanged on test set. Under this constraint, collapsing asymmetric boundary evidence into a single scalar can be brittle under polarity shifts across tasks. We propose Completion at the Boundary (CaB), which predicts an event-local completion object in the form of Boundary-Phase Tokens (Before/Hit/After), retaining two-sided boundary evidence under this discipline. CaB-When converts this completion object into a minimal, auditable switching decision (when), while CaB-How reuses the same completion object to condition action generation for boundary-stable control through handoffs (how). Using an intervention-aware E1/E2 protocol, we show that CaB improves composite execution and handoff quality on a first-person Minecraft VLA benchmark under matched capacity and deployability constraints.

Related papers

• Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling [65.03665015319457]
  We propose an action-class-oriented diagnostic framework that decomposes multi-turn failures into two modes: action-class miscalibration and action-execution failure.<n>We validate it on a panel of tool-calling models across multiple multi-turn benchmarks.
  arXiv  Detail & Related papers  (2026-09-01T09:08:15Z)
• One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI [0.0]
  We show that a remediation applied by one control can change the action, evidence, or context another control evaluates, invalidating that control's earlier judgment.<n>We formalize this coupling and give a remediate-and-regate protocol that restores per-action soundness in the current bounded, idempotent setting.<n>This is a mechanism demonstration on open payload data with a synthetic metadata layer, not a claim about production prevalence.
  arXiv  Detail & Related papers  (2026-08-18T22:24:44Z)
• BICPO-VLA: Behavior-Identified Continuation Preference Optimization for Smooth Asynchronous Vision-Language-Action Control [32.93954687398763]
  BICPO-VLA addresses the gap between request-to-handoff and request-to-handoff mismatches.<n>An instruction-aware causal history encoder identifies the behavior supported by the command and current task progress.<n>BICPO rolls the known outgoing actions to the actual handoff state and applies reference-relative Flow-DPO among behaviorally matched candidates.
  arXiv  Detail & Related papers  (2026-08-14T03:51:27Z)
• Certifying Plans under Model Mismatch: A Trilemma for Reachability from Scarce Data [5.455772242709494]
  Sim-to-real policies are designed under nominal dynamics, but target-system trials may yield only a few isolated one-step transitions.<n>We study pre-execution certification of a fixed control sequence, such as an action chunk produced by a learned policy.
  arXiv  Detail & Related papers  (2026-08-03T16:28:26Z)
• Interactive Critique-Revision Training for Reliable Structured LLM Generation [18.00222080273147]
  We propose DPA-GRPO, a paired-action training method for a two-player generator--verifier game with structured verifier interventions.<n>We analyze the unregularized game and show that positive probability on strictly lower-reward intervention or revision actions creates a profitable unilateral deviation.<n>Experiments on TaxCalc TY24 show that DPA-GRPO improves structured decision accuracy over zero-shot generation and generator-only RL baselines.
  arXiv  Detail & Related papers  (2026-05-08T17:00:38Z)
• Ghost in the Context: Measuring Policy-Carriage Failures in Decision-Time Assembly [0.0]
  LLM agents do not act on raw interaction history; they act on a bounded decision state assembled by truncation, summarization, reordering, and rewriting.<n>We study this failure mode over local Llama 3.1 8B, Qwen 2.5 7B, and Mistral 7B using judged exact constraint respect and direct audits of assembled-state visibility.
  arXiv  Detail & Related papers  (2026-05-02T18:07:42Z)
• ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures [11.399289646886968]
  We propose a framework that uses prediction and contrast to adjust deviations across three levels: actions, subgoals, and trajectories.<n>We introduce two new metrics to quantify error propagation and recovery processes in tasks.<n>Experiments show that ReCAPA achieves competitive results on embodied agent benchmarks such as VisualAgentBench, MineDojo, and AI2-THOR.
  arXiv  Detail & Related papers  (2026-04-23T02:57:50Z)
• Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols [51.56484100374058]
  We propose a paired-outcome measurement interface for auditing a single protocol step on exact-match tasks.<n>For each instance, the interface records a baseline correctness bit and a post-step correctness bit.<n>These rates predict accuracy changes and define a reusable empirical interface testable across seeds, mixtures, and pipelines.
  arXiv  Detail & Related papers  (2026-04-20T13:25:40Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• Conformal Tradeoffs: Guarantees Beyond Coverage [0.02648566468224904]
  Deployed conformal predictors are long-lived decision infrastructure operating over finite operational windows.<n> Marginal coverage does not determine deployment-facing quantities.<n>We provide a framework for operational certification and planning beyond coverage.
  arXiv  Detail & Related papers  (2026-02-20T07:58:25Z)
• When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents [50.5814495434565]
  This work makes the first effort to define and study misaligned action detection in computer-use agents (CUAs)<n>We identify three common categories in real-world CUA deployment and construct MisActBench, a benchmark of realistic trajectories with human-annotated, action-level alignment labels.<n>We propose DeAction, a practical and universal guardrail that detects misaligned actions before execution and iteratively corrects them through structured feedback.
  arXiv  Detail & Related papers  (2026-02-09T18:41:15Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• From Imitation to Refinement -- Residual RL for Precise Assembly [19.9786629249219]
  Recent advances in Behavior Cloning (BC) have made it easy to teach robots new tasks.<n>However, we find that the ease of teaching comes at the cost of unreliable performance.<n>We devise a simple yet effective method, ResiP, that overcomes the reliability problem while retaining BC's ease of teaching and long-horizon capabilities.
  arXiv  Detail & Related papers  (2024-07-23T17:44:54Z)
• Bottom-Up Temporal Action Localization with Mutual Regularization [107.39785866001868]
  State-of-the-art solutions for TAL involve evaluating the frame-level probabilities of three action-indicating phases. We introduce two regularization terms to mutually regularize the learning procedure. Experiments are performed on two popular TAL datasets, THUMOS14 and ActivityNet1.3.
  arXiv  Detail & Related papers  (2020-02-18T03:59:13Z)

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.