2026· Poster Volume 0008 The 2026 Twenty-Second International Conference on Intelligent Computing July 23-26, 2026 Toronto, Canada· 0 citations
TL;DR
This study cautions against transplanting verification into grounding pipelines and identifies calibrated abstention as a property worth preserving and proposes an abstention-aware verifier that intervenes only under sufficient candidate coverage and confidence.
Abstract
Web agents built on large vision-language models (VLMs) increasingly adopt a two-stage design: a grounding stage proposes candidate elements on a page, and an action stage decides which element to operate on and how. A natural way to strengthen such agents is to insert a pre-action verifier that re-scores the grounded candidates before acting, echoing the gains that verification and self-refinement bring to language-model reasoning. We test this assumption on the Mind2Web benchmark and report a counter-intuitive result: a GLM-4.6V pre-action verifier does not help and in fact degrades performance, low-ering the action-level step success rate from 34.8% to 23.7% on our evalua-tion subset. Through a step-level analysis we attribute this degradation to two causes. First, the offline multiple-choice protocol has limited candidate cov-erage, as the gold element is absent from the candidate set in roughly 80% of steps, so most steps are unsolvable regardless of verification. Second, and more decisively, the verifier mis-ranks candidates on the solvable steps and discards the grounding stage's calibrated abstention on the unsolvable majori-ty, so it removes a safe default without improving accuracy: it wins 5 steps but loses 20. Guided by this diagnosis, we propose an abstention-aware veri-fier that intervenes only under sufficient candidate coverage and confidence. Our study cautions against transplanting verification into grounding pipelines and identifies calibrated abstention as a property worth preserving.
A pipeline promoting an AI system publishes records claiming the thing evaluated is the thing deployed and that the evidence licensed the transition. We measure, from public material only, whether those records can express that claim and whether it holds where declared. First, a two-class documentation survey of 47 delivery platforms (20 CI/CD, 27 model-serving/agent) under one fixed three-label protocol, graded twice (second pass blind), every consulted page pinned by content hash and date. Across 188 double-graded cells we found no platform whose default record emits a content-addressed identity of the behavioral tuple (model version, instructions, tool definitions, retrieval and runtime configuration); the blind pass grades that column default on zero of 47. Immutable nominal versioning is meanwhile arriving as the agent platforms'default answer (16 of 27): version integers behind mutable pointers, a layer the artifact supply chain already found insufficient. Second, an instrument computes realized assurance depth from a pipeline's published exhaust alone and compares it with the declared depth. Applied to a frozen two-stratum frame of 30 public repositories graded twice from a hashed archive (second pass blind; cell-level agreement 23 and 19 of 30, both passes independently finding the same five full realizations), the sharpest result is a verifiability hole: seven of the 15 repositories chosen for adopting attestation tooling publish source-only releases, so the binding their workflows declare cannot be checked where declared. Where checkable it mostly checks out: five of seven measurable adopters realize the binding end to end; both shortfalls fall at identity binding. Together the results locate the field's records structurally short of justifiability, the one rung that can refuse a transition. The survey carries an expiry clock; we state what would falsify each finding.
An AI agent's rebuild is only as good as the process that produced it. Prior work found that once a model is strong enough, a multi-agent rebuild pipeline loses to the simplest approach: giving the model the original code and one instruction (AgentModernize). We present rebuild-dossier, an open-source tool that locks an application's real interface - its exact inputs and outputs - before any code is written, then enforces one-test-at-a-time building through automated checks, not written instructions alone. Three results shape this evaluation, with differing amounts of evidence. First, in a small comparison, the compliant agent failed a held-back test while the rule-breaking agent passed everything - proof that a passing suite doesn't certify correctness when tests can be gamed. Second, we tested whether this beats simply giving the weaker model the source and one instruction: tied on a small app, but lost outright on a larger one where the automated check wasn't even running - pointing to the check mechanism, not interface-locking, which held up separately. Third, every claim here is checked at three levels - the agent's own report, an automated log, and the actual files produced - catching real errors, including a bug in our own logging code, that a single level would have missed. These risks reproduce on a different model and toolchain: a stronger model followed our process three times running, something the weaker model never managed. The tool is public, MIT licensed, and reproduces end to end against our own applications.
The ORCA-bench benchmark is introduced, a benchmark that puts general-purpose coding agents in a production-fidelity oncall setting and is a lower bound on the engineering investment required before frontier coding agents can be safely entrusted with production reliability.
Albert Gong, Kyuseong Choi, Abhineet Agarwal et al.· 0 citations
How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so that verification is structural rather than post-hoc. A deterministic Executive owns all belief; a language model may only file typed proposals, and a claim is admitted only when a prediction pre-registered before acting is matched against observation by code. Two properties make the instrument a verifier of its own science, not just of the agent: every run invalidates itself when per-organ write-error, render-size, or salted-canary-echo floors are breached (four of the first eight architecture runs were invalidated, each localizing a real defect); and a render-invisible shadow reference compiles the plan the full system would have committed in every ablation cell, so drift metrics are defined even where the mechanism under test has been removed. Using this instrument we report a clean, single-variable result on a failure every long-horizon agent suffers: ablating the commitment mechanism flips goal-abandonment from 0.00 to 1.00 while binding error stays flat at 0.00 (three seeds per cell, up to 394 reference beats per run, every run gated valid). The binding channel, by contrast, does not reappear as per-beat drift when its repair is ablated -- because binding is code-owned, the failure class is structurally absorbed, its only residue appearing one layer upstream as a collapse in hypothesis formation. We report these under full disclosure that task efficacy is null (zero level completions across 52 gated runs on ARC-AGI-3), pre-registered as a structural defeater. The contribution is a verification methodology for agent development and the drift decomposition it makes measurable.
As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outcomes, unable to distinguish reliable reasoning from lucky success or attribute failures to specific process deficiencies, hindering attribution in long-horizon tasks. In this work, we present ClawTrack, a dual-assessment benchmark that simultaneously measures what an agent achieves (Task Score) and how it achieves it (Process Score). ClawTrack comprises 320 tasks across 8 domains with 25+ deterministic mock services. A Process Grader scores each reasoning turn along four dimensions (goal alignment, efficiency, information utilization, and result verification), anchored by 12,541 task-specific rubric items. Evaluating 21 models over 16,000+ trials, we find that: (1) process scores effectively attribute success and failure to specific reasoning dimensions, filtering lucky passes invisible to outcome-only evaluation; (2) the four dimensions are complementary, with result verification as the systematic bottleneck; (3) the framework is robust to evaluator choice across different judge LLMs; and (4) process-based trajectory filtering yields consistent post-training improvements across model scales.
Xingjian Wu, Xuhan Zhu, Xingchen Liu et al.· 0 citations
Web search agents powered by Large Language Models (LLMs) show strong promise, but deep research tasks expose a recurring failure mode: once an agent has produced a query, plan, or intermediate conclusion, it becomes less objective when later judging the consequences of that same action. We term this phenomenon inertia bias. To make it measurable, we introduce the IBIS benchmark, which controls the search observations while varying whether the model is evaluating the outcome of its own prior action. We find that models are substantially worse when they"own"the preceding search step, showing that self-authored action history can systematically distort subsequent judgment. We further show that this bias propagates into two forms of system-level degradation: search noise at the worker level and contextual noise at the manager level. To address this problem, we propose NIS-Agent, which applies context isolation at the two decision points most vulnerable to inertia bias: webpage triage and final-answer validation. Across GAIA, WebWalkerQA, BrowseComp, and BrowseComp-zh, NIS-Agent achieves competitive performance while reducing token cost by 33% compared to our baseline. We further train an 8B model to be intrinsically more resistant to inertia bias; under the same NIS-Agent framework, it attains average performance comparable to GPT-4o on deep research benchmarks. Our code is publicly available at https://github.com/PangSMPang/NIS-Agent.
Xiangdong Zhang, Zhanwei Zhang, Zhihang Fu et al.· 0 citations