Unzip

## Episode Summary

In this episode, we cover:

- **TAHOE: Text-to-SQL with Automated Hint Optimization from Experience** (arXiv)

- [Read more](http://arxiv.org/abs/2606.12387v1)

- **τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.10156)

- **Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization** (arXiv)

- [Read more](http://arxiv.org/abs/2606.12373v1)

- **Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.12385)

- **Building Social World Models with Large Language Models** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.11482)

---

*Sponsored by LimitLess AI*

## Episode Summary

In this episode, we cover:

- **Kwai Keye-VL-2.0 Technical Report** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.10651)

- **ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity** (arXiv)

- [Read more](http://arxiv.org/abs/2606.11150v1)

- **EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents** (arXiv)

- [Read more](http://arxiv.org/abs/2606.11182v1)

- **P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning** (arXiv)

- [Read more](http://arxiv.org/abs/2606.11152v1)

- **Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories** (arXiv)

- [Read more](http://arxiv.org/abs/2606.11176v1)

---

*Sponsored by LimitLess AI*

## Episode Summary

In this episode, we cover:

- **EmpiriGraph-Psy: A Dataset and LLM Pipeline for Extracting Empirical Relation Graphs from Psychology Abstracts** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.08362)

- **DEI: Diversity in Evolutionary Inference for Quality-Diversity Search** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2605.27130)

- **SDR: Set-Distance Rewards for Radiology Report Generation** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.00440)

- **OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics** (arXiv)

- [Read more](http://arxiv.org/abs/2606.09826v1)

- **Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.07436)

---

*Sponsored by LimitLess AI*

## Episode Summary

In this episode, we cover:

- **Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.05531)

- **Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2605.29430)

- **A Cookbook of 3D Vision: Data, Learning Paradigms, and Application** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.04291)

- **How reliable are LLMs when it comes to playing dice?** (arXiv)

- [Read more](http://arxiv.org/abs/2606.07515v1)

- **Agentopia: Long-Term Life Simulation and Learning in Agent Societies** (arXiv)

- [Read more](http://arxiv.org/abs/2606.07513v1)

---

*Sponsored by LimitLess AI*

## Episode Summary

In this episode, we cover:

- **Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for Multi-Granularity AI-Text Detection** (arXiv)

- [Read more](http://arxiv.org/abs/2606.06481v1)

- **Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators** (arXiv)

- [Read more](http://arxiv.org/abs/2606.06476v1)

- **Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.06492)

- **You Only Index Once: Cross-Layer Sparse Attention with Shared Routing** (arXiv)

- [Read more](http://arxiv.org/abs/2606.06467v1)

- **Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.06443)

---

*Sponsored by LimitLess AI*

## Episode Summary

In this episode, we cover:

- **MAOAM: Unified Object and Material Selection with Vision-Language Models** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.04880)

- **The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.02956)

- **AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.06155)

- **ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.00644)

- **Regret Minimization with Adaptive Opponents in Repeated Games** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.06486)

---

*Sponsored by LimitLess AI*

## Episode Summary

In this episode, we cover:

- **AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.05557)

- **LLM Anonymization Against Agentic Re-Identification** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2605.30848)

- **Benchmark Everything Everywhere All at Once** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.06462)

- **PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding** (arXiv)

- [Read more](http://arxiv.org/abs/2606.06485v1)

- **SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.01317)

---

*Sponsored by LimitLess AI*

## Episode Summary

In this episode, we cover:

- **Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.04978)

- **Large Language Models Hack Rewards, and Society** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.04075)

- **SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.00825)

- **When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.03712)

- **Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.05112)

---

*Sponsored by LimitLess AI*

## Episode Summary

In this episode, we cover:

- **MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.04688)

- **Streaming Communication in Multi-Agent Reasoning** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.05158)

- **Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.03577)

- **AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.03031)

- **Score-Control for Hallucination Reduction in Diffusion Models** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.00377)

---

*Sponsored by LimitLess AI*

## Episode Summary

In this episode, we cover:

- **The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2605.29087)

- **TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.02320)

- **ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents** (arXiv)

- [Read more](http://arxiv.org/abs/2606.02568v1)

- **Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2605.30501)

- **Policy and World Modeling Co-Training for Language Agents** (Hugging Face Daily)

- [Read more](https://huggingface.co/papers/2606.02388)

---

*Sponsored by LimitLess AI*