·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
OpenAI bets on families as ChatGPT goes deeper into households4h◆Svarna: An Open Corpus Workbench for Modern Greek14h◆PLURAL: A Global Dataset for Value Alignment14h◆Validating LLMs in social science: Epistemic threats and emerging norms14h◆How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism14h◆WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search14h◆Temporal Preference Concepts and their Functions in a Large Language Model14h◆UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks14h◆When Synthetic Speech Is All You Have: Better Call GRPO14h◆ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation14h◆Towards Isolated Interventions via Almost Orthogonal Features in Language Models14h◆MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction14h◆Peer-Predictive Self-Training for Language Model Reasoning14h◆DeepTutor: Towards Agentic Personalized Tutoring14h◆COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation14h◆Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator14h◆CausalDS: Benchmarking Causal Reasoning in Data-Science Agents14h◆Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization14h◆Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition14h◆Where do LLMs Fall Short in CBT-Guided Affective Reasoning?14h◆OpenAI bets on families as ChatGPT goes deeper into households4h◆Svarna: An Open Corpus Workbench for Modern Greek14h◆PLURAL: A Global Dataset for Value Alignment14h◆Validating LLMs in social science: Epistemic threats and emerging norms14h◆How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism14h◆WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search14h◆Temporal Preference Concepts and their Functions in a Large Language Model14h◆UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks14h◆When Synthetic Speech Is All You Have: Better Call GRPO14h◆ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation14h◆Towards Isolated Interventions via Almost Orthogonal Features in Language Models14h◆MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction14h◆Peer-Predictive Self-Training for Language Model Reasoning14h◆DeepTutor: Towards Agentic Personalized Tutoring14h◆COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation14h◆Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator14h◆CausalDS: Benchmarking Causal Reasoning in Data-Science Agents14h◆Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization14h◆Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition14h◆Where do LLMs Fall Short in CBT-Guided Affective Reasoning?14h◆
News/AI-Assisted Discovery of Convex Relaxations via Dual Agents
arxiv
PublishedJuly 1, 2026 at 4:00 AM

AI-Assisted Discovery of Convex Relaxations via Dual Agents

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

arXiv:2606.31182v1 Announce Type: new Abstract: Recent work shows that LLM agents can improve sharp-constant inequalities by searching for extremal constructions, which yield upper bounds. We address the complementary side: a lower bound holds for every admissible function and follows from a convex

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 Greek14harxivPLURAL: A Global Dataset for Value Alignment14harxivValidating LLMs in social science: Epistemic threats and emerging norms14harxivHow Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism14h
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