·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Mach2: Scientific Discovery Platform with Deterministic Execution Constraints7h◆OverServe: Resource Amplification Attacks on SaaS Agents via Tool--Prompt Co-Design7h◆Discharge Summary Generation Is Not Just Summarization: A Reality Check for Evaluation7h◆Do Large Language Models Show Racial and Sex Bias in Pain Management? A Counterfactual Audit of GPT, Claude, Gemini, Llama, DeepSeek and Qwen7h◆The Posterior-Prior Epistemic Gap: When World Model Imagination Fails to Carry Task-Relevant Signals7h◆Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences7h◆Who Moved the Frontier? Paying Open Frontier Challenges with Free Identities7h◆Breaking Bad: "Going Badly" Activations Drive Reward Hacking7h◆QSim-Arena: an evolving developer for quantum simulation advantage7h◆Moving Beyond the DRW Model: Learning Quasar Variability with Generative Models7h◆Prototypes of the Mind: A Unified Framework for Probing the Visual Brain7h◆CFGComposer: Compositional Audio-Text-to-Motion Generation via Copula Score Correction7h◆When Does Learned Constraint Selection Pay in Security-Constrained Optimisation? A Boundary Map from SCOPF to Unit Commitment7h◆Multi-View 3D Reconstruction Using V-JEPA Features7h◆GingivitisSeg: A Public Dataset and Comparative Benchmark for Gingivitis Segmentation in Intraoral Images7h◆Can Model Answer Probabilities Represent Survey Populations? Conditional Prediction and Joint Validity in Jev Survey Simulation7h◆Bug Finding With Agentic Symbolic Execution7h◆Are Scaling Laws of Universal MLIPs Universal?7h◆Contrastive Bootstrap Representation Learning for Label-Efficient Agricultural Image Classification7h◆Learning-Based Interpolation of Detector Gaps in Photon-Counting X-ray Imaging7h◆Mach2: Scientific Discovery Platform with Deterministic Execution Constraints7h◆OverServe: Resource Amplification Attacks on SaaS Agents via Tool--Prompt Co-Design7h◆Discharge Summary Generation Is Not Just Summarization: A Reality Check for Evaluation7h◆Do Large Language Models Show Racial and Sex Bias in Pain Management? A Counterfactual Audit of GPT, Claude, Gemini, Llama, DeepSeek and Qwen7h◆The Posterior-Prior Epistemic Gap: When World Model Imagination Fails to Carry Task-Relevant Signals7h◆Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences7h◆Who Moved the Frontier? Paying Open Frontier Challenges with Free Identities7h◆Breaking Bad: "Going Badly" Activations Drive Reward Hacking7h◆QSim-Arena: an evolving developer for quantum simulation advantage7h◆Moving Beyond the DRW Model: Learning Quasar Variability with Generative Models7h◆Prototypes of the Mind: A Unified Framework for Probing the Visual Brain7h◆CFGComposer: Compositional Audio-Text-to-Motion Generation via Copula Score Correction7h◆When Does Learned Constraint Selection Pay in Security-Constrained Optimisation? A Boundary Map from SCOPF to Unit Commitment7h◆Multi-View 3D Reconstruction Using V-JEPA Features7h◆GingivitisSeg: A Public Dataset and Comparative Benchmark for Gingivitis Segmentation in Intraoral Images7h◆Can Model Answer Probabilities Represent Survey Populations? Conditional Prediction and Joint Validity in Jev Survey Simulation7h◆Bug Finding With Agentic Symbolic Execution7h◆Are Scaling Laws of Universal MLIPs Universal?7h◆Contrastive Bootstrap Representation Learning for Label-Efficient Agricultural Image Classification7h◆Learning-Based Interpolation of Detector Gaps in Photon-Counting X-ray Imaging7h◆
News/Folio: Recoverable Multi-Resolution Context Folding for Long-Horizon Language Agents
arxiv
PublishedNovember 14, 2026 at 5:00 AM

Folio: Recoverable Multi-Resolution Context Folding for Long-Horizon Language Agents

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

arXiv:2611.16627v1 Announce Type: new Abstract: Long-horizon language agents accumulate tool results and replies until the history no longer fits the context window. Current agents shrink this history by having a model summarize it, so each compaction rereads and rewrites the history it replaces, an

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

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

Your email is used only to send The Bubble Brief. Privacy policy

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
arxivMach2: Scientific Discovery Platform with Deterministic Execution Constraints7harxivOverServe: Resource Amplification Attacks on SaaS Agents via Tool--Prompt Co-Design7harxivDischarge Summary Generation Is Not Just Summarization: A Reality Check for Evaluation7harxivDo Large Language Models Show Racial and Sex Bias in Pain Management? A Counterfactual Audit of GPT, Claude, Gemini, Llama, DeepSeek and Qwen7h
The Bubble Brief
MON · WED · FRI

Read AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

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

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews