·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Retrieval Augmented Generation Compositionality43m◆VeriEvolve: Evaluator-First Evolution for Tool-Using Agents43m◆TNODEV: Toolbox for Neural ODE Verification43m◆Learning to Interfere in Non-Orthogonal Multiple-Access Joint Source-Channel Coding43m◆On the Expressive Power and Limitations of Multi-Layer SSMs43m◆From Weather to Enhanced Weathering: Weather Foundation Models for Carbon Dioxide Removal at Operational Scale43m◆Predictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression43m◆A Generalisation Signal Need Not Be a Model-Selection Signal43m◆Mitigating Reward Hacking in Realistic Scenarios Through Representation Engineering43m◆ChemBART: Pre-training a Reaction Language Model for Comprehensive Synthesis Planning43m◆Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?43m◆AnnoCaseLaw: Legal Annotation Benchmark of Civil Negligence43m◆Improved Training of Strong Stochastic Flow Maps43m◆Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation43m◆HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second43m◆Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection43m◆Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models43m◆Conditional Optimal Bridge for Riemannian Activation Steering43m◆RL-IF: Tracking Non-local Training Data Influence for Online Reinforcement Learning43m◆Unintended Side Effects of Value Training in LLMs43m◆Retrieval Augmented Generation Compositionality43m◆VeriEvolve: Evaluator-First Evolution for Tool-Using Agents43m◆TNODEV: Toolbox for Neural ODE Verification43m◆Learning to Interfere in Non-Orthogonal Multiple-Access Joint Source-Channel Coding43m◆On the Expressive Power and Limitations of Multi-Layer SSMs43m◆From Weather to Enhanced Weathering: Weather Foundation Models for Carbon Dioxide Removal at Operational Scale43m◆Predictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression43m◆A Generalisation Signal Need Not Be a Model-Selection Signal43m◆Mitigating Reward Hacking in Realistic Scenarios Through Representation Engineering43m◆ChemBART: Pre-training a Reaction Language Model for Comprehensive Synthesis Planning43m◆Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?43m◆AnnoCaseLaw: Legal Annotation Benchmark of Civil Negligence43m◆Improved Training of Strong Stochastic Flow Maps43m◆Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation43m◆HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second43m◆Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection43m◆Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models43m◆Conditional Optimal Bridge for Riemannian Activation Steering43m◆RL-IF: Tracking Non-local Training Data Influence for Online Reinforcement Learning43m◆Unintended Side Effects of Value Training in LLMs43m◆
News/QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems
arxiv
PublishedMay 1, 2026 at 4:00 AM
▲bullish

QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems

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

arXiv:2604.24021v2 Announce Type: replace Abstract: We explore a central question in AI for mathematics: can AI systems produce original, nontrivial proofs for open research problems? Despite strong benchmark performance, producing genuinely novel proofs remains an outstanding challenge for LLMs. Th

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
Mentioned models
02
  • 01
    LLMs
  • 02
    QED
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#proof-generation#open-source#mathematics#research

No replies yet. Be first.

Mentioned models
02
  • 01
    LLMs
  • 02
    QED
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#proof-generation#open-source#mathematics#research

Related coverage

More from ARXIV
arxivRetrieval Augmented Generation Compositionality43marxivVeriEvolve: Evaluator-First Evolution for Tool-Using Agents43marxivTNODEV: Toolbox for Neural ODE Verification43marxivLearning to Interfere in Non-Orthogonal Multiple-Access Joint Source-Channel Coding43m
The Bubble Brief
MON · WED · FRI

Read proof-generation 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