·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees3h◆Limite 1B - Violetto: Technical Report3h◆MedGuardBench: A Patient-Oriented Benchmark for Personalized Guardrail Development3h◆Can You Undo It? Reversibility Classes for AI Agent Actions3h◆ATLAS-Finance: Benchmarking AI Agents in Realistic Banking Environments3h◆EvoDisco: Strategy Discovery for Evolving Agent Memory3h◆From Sorry to QED: Refining LLM Math Proofs via Angelic Execution3h◆RegimeCouncil: Paired-Evidence Routing For Memory Conflict Governance In LLM Agents3h◆TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks3h◆LoCaR: Localized Canvas Retrieval With Frozen Vision-Language Model3h◆EgoLink: Egocentric Language-Vision Interactive Network Knowledge Challenge Summary3h◆AdaFlowLite: Scalable and Non-blocking Inference on Asynchronous Mobile Data3h◆Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning3h◆Scaling Causal Reasoning with Increasingly Complex Causal Simulators3h◆CardioLoom: A Report-Guided Electrocardiogram Foundation Model for Cross-Domain Cardiovascular Phenotyping3h◆ICA Lens: Non-Gaussianity Reveals Interpretable Directions in Language Models3h◆REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation3h◆Cassette-Editor: Shared Timeline Semantics for Human and Agent Editing3h◆WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining3h◆Multi-Estimate Elicitation Does Not Uniformly Debias Language Model Judgments3h◆Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees3h◆Limite 1B - Violetto: Technical Report3h◆MedGuardBench: A Patient-Oriented Benchmark for Personalized Guardrail Development3h◆Can You Undo It? Reversibility Classes for AI Agent Actions3h◆ATLAS-Finance: Benchmarking AI Agents in Realistic Banking Environments3h◆EvoDisco: Strategy Discovery for Evolving Agent Memory3h◆From Sorry to QED: Refining LLM Math Proofs via Angelic Execution3h◆RegimeCouncil: Paired-Evidence Routing For Memory Conflict Governance In LLM Agents3h◆TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks3h◆LoCaR: Localized Canvas Retrieval With Frozen Vision-Language Model3h◆EgoLink: Egocentric Language-Vision Interactive Network Knowledge Challenge Summary3h◆AdaFlowLite: Scalable and Non-blocking Inference on Asynchronous Mobile Data3h◆Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning3h◆Scaling Causal Reasoning with Increasingly Complex Causal Simulators3h◆CardioLoom: A Report-Guided Electrocardiogram Foundation Model for Cross-Domain Cardiovascular Phenotyping3h◆ICA Lens: Non-Gaussianity Reveals Interpretable Directions in Language Models3h◆REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation3h◆Cassette-Editor: Shared Timeline Semantics for Human and Agent Editing3h◆WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining3h◆Multi-Estimate Elicitation Does Not Uniformly Debias Language Model Judgments3h◆
News/From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
arxiv
PublishedNovember 18, 2026 at 5:00 AM

From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment

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

arXiv:2511.19218v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly power web-facing applications, including conversational assistants and content services, where open user interaction exposes them to diverse safety threats and adaptive attacks. In particular, jailbre

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
arxivGradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees3harxivLimite 1B - Violetto: Technical Report3harxivMedGuardBench: A Patient-Oriented Benchmark for Personalized Guardrail Development3harxivCan You Undo It? Reversibility Classes for AI Agent Actions3h
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