·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Svarna: An Open Corpus Workbench for Modern Greek5m◆PLURAL: A Global Dataset for Value Alignment5m◆Validating LLMs in social science: Epistemic threats and emerging norms5m◆How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism5m◆WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search5m◆Temporal Preference Concepts and their Functions in a Large Language Model5m◆UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks5m◆When Synthetic Speech Is All You Have: Better Call GRPO5m◆ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation5m◆Towards Isolated Interventions via Almost Orthogonal Features in Language Models5m◆MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction5m◆Peer-Predictive Self-Training for Language Model Reasoning5m◆DeepTutor: Towards Agentic Personalized Tutoring5m◆COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation5m◆Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator5m◆CausalDS: Benchmarking Causal Reasoning in Data-Science Agents5m◆Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization5m◆Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition5m◆Where do LLMs Fall Short in CBT-Guided Affective Reasoning?5m◆Holographic Neural PCFG for Unsupervised Parsing5m◆Svarna: An Open Corpus Workbench for Modern Greek5m◆PLURAL: A Global Dataset for Value Alignment5m◆Validating LLMs in social science: Epistemic threats and emerging norms5m◆How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism5m◆WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search5m◆Temporal Preference Concepts and their Functions in a Large Language Model5m◆UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks5m◆When Synthetic Speech Is All You Have: Better Call GRPO5m◆ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation5m◆Towards Isolated Interventions via Almost Orthogonal Features in Language Models5m◆MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction5m◆Peer-Predictive Self-Training for Language Model Reasoning5m◆DeepTutor: Towards Agentic Personalized Tutoring5m◆COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation5m◆Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator5m◆CausalDS: Benchmarking Causal Reasoning in Data-Science Agents5m◆Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization5m◆Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition5m◆Where do LLMs Fall Short in CBT-Guided Affective Reasoning?5m◆Holographic Neural PCFG for Unsupervised Parsing5m◆
News/OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories
arxiv
PublishedMay 29, 2026 at 4:00 AM

OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.29253v1 Announce Type: new Abstract: Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or capability-boundary o

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSvarna: An Open Corpus Workbench for Modern Greek5marxivPLURAL: A Global Dataset for Value Alignment5marxivValidating LLMs in social science: Epistemic threats and emerging norms5marxivHow Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism5m
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews