Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents

• URL: http://arxiv.org/abs/2605.08747v3
• Date: Thu, 14 May 2026 03:36:04 GMT
• Title: Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents
• Abstract summary: VIGIL is an evaluation framework that makes terminal commitment independently measurable.<n>Under VIGIL's default protocol, agents observe only egocentric RGB, receive no action-success signals, and must end each episode with a semantic report checked deterministically against hidden world state.<n>This yields two separate scores: world-state completion (W) and benchmark success (B)
• Score: 11.233308795768465
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Standard embodied evaluations do not independently score whether an agent correctly commits to task completion at episode closure, a capacity we call terminal commitment. Behaviorally distinct failures--never completing the task, completing it but failing to stop, and reporting success without sufficient evidence--collapse into the same benchmark failure. We introduce VIGIL, an evaluation framework that makes terminal commitment independently measurable. Under VIGIL's default protocol, agents observe only egocentric RGB, receive no action-success signals, and must end each episode with a semantic report checked deterministically against hidden world state. This yields two separate scores: world-state completion (W) and benchmark success (B), where B additionally requires a correct terminal report. This decoupling makes four outcome categories distinguishable: missed execution, post-attainment drift, unsupported commitment, and verified success. Across 20 models on 1,000 frozen episodes, systems with comparable W differ by up to 19.7 pp in B: one model converts achieved states into correct reports, while another with near-identical execution drifts past the goal without closing. An action-feedback intervention further tests the separation: execution-oriented signals improve W broadly, yet commitment failures persist in models that do not already ground terminal reports in the achieved state. VIGIL provides a protocol that makes terminal commitment independently visible and scorable.

Related papers

• IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier [0.0]
  All 18 audited benchmarks score advertised model identifiers.<n>A gold-blind capability-binding preflight verifies that a route can execute the evaluation contract before any task reaches it.<n>A reliability-inclusive first-pass scoring rule keeps failure in the score while keeping unsupported capability out.
  arXiv  Detail & Related papers  (2026-09-09T17:31:29Z)
• VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement [57.86962208273888]
  We present an auditable physical-verification system in which a text-only planner compiles the prompt into typed physical obligations.<n>Each action returns a provenance-carrying evidence record whose payload, when usable, is either a typed measurement or an explicitly tagged learned state.<n>We anchor evaluation in a 1,500-clip corpus of human-annotated flaw records that localize real generation failures in prompt reference, space, and time.
  arXiv  Detail & Related papers  (2026-09-02T20:36:45Z)
• Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents [16.24087700490158]
  Large language model agents are increasingly deployed as autonomous loops.<n>We show that this is a failure of composition rather than an implementation detail.<n>We present LoopHarness, which restores a persistent, non-decaying safety state at the loop level.
  arXiv  Detail & Related papers  (2026-08-27T13:52:31Z)
• ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices [48.36933831982682]
  We introduce ADeptS-Bench, a trustworthiness benchmark grounded in the ADEPTS capability framework.<n>The Safety stream provides paired benign/malicious tasks with threats embedded in the visual interface.<n>The Disambiguation stream evaluates whether agents seek clarification when intent is ambiguous.
  arXiv  Detail & Related papers  (2026-08-25T23:21:57Z)
• Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol [3.202978695204522]
  Language-model agents can improve after failure or carry text across episodes without revising what counts as success.<n>We evaluate CMB-0.1 on twelve cross-domain cases and four arms.<n>No model trial satisfies all five conditions, but this zero does not establish general capability absence.
  arXiv  Detail & Related papers  (2026-08-21T04:21:28Z)
• When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation [0.0]
  Current agent evaluations score models on the state visible at the end of a stopped run which they count as one trial.<n> interpreting the score as a final result would require two conditions that the endpoint does not necessarily establish: outcome finality and cross-unit separation.<n>We argue that a final label is justified only when anything that could still change the claimed outcome is resolved, bounded, or retained as uncertainty.
  arXiv  Detail & Related papers  (2026-08-14T23:39:47Z)
• Ontology-Grounded World Models for Failure Diagnosis and Closed-Loop Repair in Physical AI Systems [0.815557531820863]
  Onto-EV-WM is a diagnosis and verification-gated correction interface layered above EV-WM.<n>Onto-EV-WM succeeds on 8,526 tasks, with suite-level success rates of 65.98% for LIBERO-10, 91.39% for LIBERO-Goal, and 91.38% for both LIBERO-Object and LIBERO-Spatial.
  arXiv  Detail & Related papers  (2026-08-14T03:13:57Z)
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents [58.49879338545782]
  Long-horizon tasks are common in real-world robotic deployments, yet failure detection for such tasks remains underexplored.<n>We present Foresight, a failure detection framework that monitors manipulation trajectories using latent representations from an action-conditioned world model.<n>Our results suggest that action-conditioned world-model embeddings provide a scalable representation for reliable failure monitoring in long-horizon manipulation.
  arXiv  Detail & Related papers  (2026-06-22T09:32:28Z)
• What Accuracy and Gradient Cosine Miss: Evaluating Feedback Alignment via Scale Stability, Reference Validity, and Depth Utility [48.10132234701036]
  We propose a diagnostic evaluation protocol based on three checks -- scale stability, reference validity, and depth utility -- together with per-layer rather than aggregate cosine reporting.<n>Across multiple architectures and methods, our protocol identifies all failures with wide calibration margins.
  arXiv  Detail & Related papers  (2026-06-19T06:04:17Z)
• Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL [76.45061154544568]
  Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels.<n>Recent systems report strong reasoning gains, but collapse and instability are widely observed and poorly understood.<n>We argue instead that self-play stability is governed by two distinct levers: a data-level gate that decides which proposer-generated tasks enter the training pool, and the reward signal that updates the policy on tasks already admitted.
  arXiv  Detail & Related papers  (2026-05-21T09:19:23Z)
• Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents [2.3488056916440856]
  Existing benchmarks score whether the pipeline runs, ignoring whether the agent recognized the task was underspecified.<n>We introduce Ambig-DS, two diagnostic suites: one for prediction-target ambiguity and one for evaluation-objective ambiguity.<n>For every task we pair the original, fully specified version with an ambiguous variant produced by controlled edits.
  arXiv  Detail & Related papers  (2026-05-10T18:34:12Z)
• Reconstructive Authority Model: Runtime Execution Validity Under Partial Observability [0.4929694290403903]
  We show that an authenticated projection of state is necessary but never sufficient for execution validity.<n>We introduce the Reconstructive Authority Model (RAM), which separates integrity from coverage.<n>We present a hybrid RAM+Attestation architecture with privilege-narrowing insufficiency.
  arXiv  Detail & Related papers  (2026-04-24T13:19:27Z)
• Pando: Do Interpretability Methods Work When Models Won't Explain Themselves? [53.07826484214082]
  We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis.<n>Pando predicts held-out model decisions from $10$ labeled query-response pairs.<n>When explanations are faithful, black-box elicitation matches or exceeds all white-box methods.
  arXiv  Detail & Related papers  (2026-04-13T06:42:24Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry [82.93104394404781]
  General-purpose world models promise scalable policy evaluation, optimization, and planning.<n>We propose World Action Verifier (WAV), a framework that enables world models to identify their own prediction errors and self-improve.
  arXiv  Detail & Related papers  (2026-04-02T12:48:36Z)
• Toward Faithful Segmentation Attribution via Benchmarking and Dual-Evidence Fusion [4.726028690278432]
  We introduce a reproducible benchmark that tests intervention-based faithfulness, off-target leakage, runtime, and on Pascal VOC.<n>We propose Dual-Evidence Attribution (DEA), a lightweight correction that fuses evidence with region-level intervention signals.
  arXiv  Detail & Related papers  (2026-03-23T22:52:00Z)
• vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models [58.633451339058986]
  VLA models are typically evaluated using per benchmark scripts maintained independently by each model repository.<n>We present vla eval, an open source evaluation harness that decouples model inference from benchmark execution.<n>A complete evaluation requires only two commands: vla eval serve and vla eval run.
  arXiv  Detail & Related papers  (2026-03-14T14:38:53Z)
• Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks [0.38991526486631006]
  We argue that many reliability failures are caused by drift from a task's latent solution structure, not capability failures.<n>We establish this causally using a natural experiment that holds model capability and task difficulty fixed by construction.
  arXiv  Detail & Related papers  (2026-02-22T02:37:57Z)
• OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence [0.0]
  We introduce OpenSec, a dual-control reinforcement learning environment that evaluates defensive incident response agents.<n>Unlike static capability benchmarks, OpenSec scores world-state-changing containment actions under adversarial evidence.<n>We find consistent over-triggering in this setting: GPT-5.2, Gemini 3, and DeepSeek execute containment in 100% of episodes with 90-97% false positive rates.
  arXiv  Detail & Related papers  (2026-01-28T22:12:54Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems [48.971606069204825]
  DoVer is an intervention-driven debug framework for large language model (LLM)-based multi-agent systems.<n>It augments hypothesis generation with active verification through targeted interventions.<n>DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses.
  arXiv  Detail & Related papers  (2025-12-07T09:23:48Z)

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.