·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
OPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining6h◆Stochastic Sampling is Epistemically Shallow: The Dimensionality Gap Between Temperature Variation and Model Diversity in LLMs6h◆DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions6h◆PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs6h◆Incomplete Prompt Jailbreaks in Large Language Models6h◆Directional Hallucinations: Ideological Drift in News-Grounded LLM Question Answering6h◆Autonomous Topology Mutation: Safe Runtime Restructuring for Multi-Agent LLM Systems with Capability, State, and Shadow Invariants6h◆DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making6h◆Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under Adversarial Mutation6h◆Optimizing Hypergraph-Based RAG: Toward Better Fact Extraction and Chunk Retrieval6h◆DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers6h◆StrideDiffusion: Accelerating Diffusion Models for Time-series Generation6h◆Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs6h◆Efficient and Interpretable Body-Based Emotion Recognition with Lightweight Temporal Convolutional Networks6h◆Auditing Evidence Use in Medical LLM Diagnosis6h◆Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions6h◆Representing Entity Importance in AI Knowledge Systems: A Dual-Signal Framework of Audience Evaluation and Structural Authority6h◆SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration6h◆From Scalars to Time Series: Rethinking Implicit Neural Representations for Time-Varying Volumetric Data6h◆V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure6h◆OPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining6h◆Stochastic Sampling is Epistemically Shallow: The Dimensionality Gap Between Temperature Variation and Model Diversity in LLMs6h◆DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions6h◆PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs6h◆Incomplete Prompt Jailbreaks in Large Language Models6h◆Directional Hallucinations: Ideological Drift in News-Grounded LLM Question Answering6h◆Autonomous Topology Mutation: Safe Runtime Restructuring for Multi-Agent LLM Systems with Capability, State, and Shadow Invariants6h◆DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making6h◆Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under Adversarial Mutation6h◆Optimizing Hypergraph-Based RAG: Toward Better Fact Extraction and Chunk Retrieval6h◆DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers6h◆StrideDiffusion: Accelerating Diffusion Models for Time-series Generation6h◆Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs6h◆Efficient and Interpretable Body-Based Emotion Recognition with Lightweight Temporal Convolutional Networks6h◆Auditing Evidence Use in Medical LLM Diagnosis6h◆Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions6h◆Representing Entity Importance in AI Knowledge Systems: A Dual-Signal Framework of Audience Evaluation and Structural Authority6h◆SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration6h◆From Scalars to Time Series: Rethinking Implicit Neural Representations for Time-Varying Volumetric Data6h◆V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure6h◆
News/AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use
arxiv
PublishedJuly 24, 2026 at 4:00 AM

AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use

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

arXiv:2607.20536v1 Announce Type: new Abstract: Tool-use agents that address day-to-day digital tasks such as ordering groceries must not only operate applications, but also interact with the user, e.g., to ask clarification questions, prompt for confirmation, and inform the user when the instructio

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
arxivOPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining6harxivStochastic Sampling is Epistemically Shallow: The Dimensionality Gap Between Temperature Variation and Model Diversity in LLMs6harxivDecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions6harxivPlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs6h
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