number theory
30 articles about number theory in AI news
When AI Agents Need to Read Minds: The Complex Reality of Theory of Mind in Multi-LLM Systems
New research reveals that adding Theory of Mind capabilities to multi-agent AI systems doesn't guarantee better coordination. The effectiveness depends on underlying LLM capabilities, creating complex interdependencies in collaborative decision-making.
Researchers Apply Distributed Systems Theory to LLM Teams, Revealing O(n²) Communication Bottlenecks
A new paper applies decades-old distributed computing principles to LLM multi-agent systems, finding identical coordination problems: O(n²) communication bottlenecks, straggler delays, and consistency conflicts.
Agent Psychometrics: New Framework Predicts Task-Level Success in Agentic Coding Benchmarks with 0.81 AUC
A new research paper introduces a framework using Item Response Theory and task features to predict success on individual agentic coding tasks, achieving 0.81 AUC. This enables benchmark designers to calibrate difficulty without expensive evaluations.
GitHub Repository 'Math Textbooks' Aggregates Hundreds of Free University-Level Math Texts
An unmaintained GitHub repository has compiled links to hundreds of free, legally-hosted math textbooks from universities like MIT, Harvard, and Stanford. The collection spans from undergraduate calculus to graduate-level quantum field theory.
Bridging the Gap: New RL Method Delivers Stability Guarantees with Finite Data
Researchers have developed a novel reinforcement learning approach that provides probabilistic stability guarantees using only finite data samples. The method leverages Lyapunov stability theory to ensure control systems remain stable during learning, addressing a critical challenge in deploying RL for real-world applications.
GPT-5.4 Pro Solves 60-Year-Old Erdős Problem #1196, Finds 'Book Proof'
OpenAI's GPT-5.4 Pro solved Erdős Problem #1196, a 60-year-old conjecture on primitive sets, in ~80 minutes. The AI discovered a purely analytic proof using von Mangoldt weights, rejecting the standard probabilistic approach used by mathematicians since 1935.
Entropy-Guided Branching Boosts Agent Success 15% on New SLATE E-commerce
A new paper introduces SLATE, a large-scale benchmark for evaluating tool-using AI agents, and Entropy-Guided Branching (EGB), an algorithm that improves task success rates by 15% by dynamically expanding search where the model is uncertain.
AI Engineer Gurisingh Turns Ed Thorp's Trading System into 10 ChatGPT Prompts
AI engineer Gurisingh has distilled the quantitative, probabilistic trading system of Ed Thorp—who beat blackjack and ran a 29-year winning hedge fund—into 10 actionable prompts for AI agents.
Anthropic Reportedly Deploys AI Model for Zero-Day Vulnerability Discovery
Anthropic has reportedly deployed a frontier AI model for discovering zero-day software vulnerabilities. The model is claimed to have found flaws in code audited by humans for decades.
OpenAI Solves Five Erdős Problems with Internal AI Model
OpenAI researchers have reportedly solved five additional unsolved Erdős problems using an internal AI model. This demonstrates significant progress in AI's ability to tackle complex, open-ended mathematical reasoning.
arXiv Paper Proposes Federated Multi-Agent System with AI Critics for Network Fault Analysis
A new arXiv paper introduces a collaborative control algorithm for AI agents and critics in a federated multi-agent system, providing convergence guarantees and applying it to network telemetry fault detection. The system maintains agent privacy and scales with O(m) communication overhead for m modalities.
arXiv Paper Proposes 'Connections' Word Game as New Benchmark for AI Agent Social Intelligence
A new arXiv preprint introduces the improvisational word game 'Connections' as a benchmark for evaluating social intelligence in AI agents. It requires agents to gauge the cognitive states of others, testing collaborative reasoning beyond individual knowledge retrieval.
TPC-CMA Framework Reduces CLIP Modality Gap by 82.3%, Boosts Captioning CIDEr by 57.1%
Researchers propose TPC-CMA, a three-phase fine-tuning curriculum that reduces the modality gap in CLIP-like models by 82.3%, improving clustering ARI from 0.318 to 0.516 and captioning CIDEr by 57.1%.
UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems
A new arXiv paper introduces UniMixer, a unified scaling architecture for recommender systems. It bridges attention-based, TokenMixer-based, and factorization-machine-based methods into a single theoretical framework, aiming to improve parameter efficiency and scaling return on investment (ROI).
DeepMind Secretly Assembled ~20-Person Team to Train AI for High-Frequency Trading, Aiming at Renaissance
Demis Hassabis formed a covert ~20-researcher team within DeepMind to develop AI-powered high-frequency trading algorithms, reportedly targeting rival Renaissance Technologies. Google leadership disapproved, leading to the project's quiet termination.
OpenAI Internal Model Reportedly Solves Three New Erdős Problems, Marking AI Advance in Pure Mathematics
An internal AI model at OpenAI has reportedly solved three previously unsolved mathematical problems from the Erdős collection. This development signals a potential leap in AI's capacity for abstract reasoning and formal theorem proving.
Morgan Stanley Predicts 10x Compute Spike to Double AI Intelligence, Highlights 18 GW Energy Crisis
Morgan Stanley forecasts a massive AI leap from a 10x increase in training compute, but warns of an 18-gigawatt U.S. power shortfall by 2028. The report claims GPT-5.4 matches human experts with 83% on GDPVal.
OpenCSF: A 1.5TB Free Computer Science Library Emerges from Unstructured Web Data
A new open-source dataset called OpenCSF has been compiled, containing 1.5TB of computer science materials scraped from public web sources. It provides a massive, free corpus for AI training and research in software engineering and CS education.
AgentComm-Bench Exposes Catastrophic Failure Modes in Cooperative Embodied AI Under Real-World Network Conditions
Researchers introduce AgentComm-Bench, a benchmark that stress-tests multi-agent embodied AI systems under six real-world network impairments. It reveals performance drops of over 96% in navigation and 85% in perception F1, highlighting a critical gap between lab evaluations and deployable systems.
Terence Tao on AI and Mathematics: Collaboration, Not Replacement, for Problems Like Riemann Hypothesis
Fields Medalist Terence Tao suggests AI may not solve problems like the Riemann Hypothesis alone, but through a 'collaboration we can't yet imagine' blending AI power with human insight.
Terence Tao on AI's Impact: 'The Way We Do Everything, Including Mathematics, Will Change'
Fields Medalist Terence Tao states we are entering an unpredictable era where AI will fundamentally change how we do everything, including mathematics. He expressed a personal preference for a more stable, 'boring' period of continuity.
Terence Tao: AI's 'Brute-Test' Approach to Math Research Could Narrow Human Efficiency Gap
Mathematician Terence Tao observes AI can synthesize millions of papers and brute-force test ideas, while humans rely on pattern recognition from few examples. He suggests the gap may narrow as AI systems develop world models, causal reasoning, and active learning.
New Research Reveals Fundamental Limitations of Vector Embeddings for Retrieval
A new theoretical paper demonstrates that embedding-based retrieval systems have inherent limitations in representing complex relevance relationships, even with simple queries. This challenges the assumption that better training data alone can solve all retrieval problems.
Terence Tao Reveals AI's Mathematical Breakthroughs: Unique Proofs Emerge from Machine Intelligence
Fields Medalist Terence Tao reports that AI systems are now generating unique mathematical proofs that human mathematicians find genuinely novel and interesting, marking a significant milestone in AI's intellectual capabilities.
Mathematics Enters New Era as AI Generates Novel Proofs, Says Fields Medalist Terence Tao
Fields Medalist Terence Tao reveals AI is now producing unique mathematical proofs, though verification remains a bottleneck. He argues that to fully leverage AI, mathematicians must design problems that are easily checkable by both humans and machines.
The Autonomous Army Dilemma: Anthropic CEO Warns of 10 Million Drone Forces Without Human Morality
Anthropic CEO Dario Amodei raises urgent concerns about autonomous military systems, questioning how future armies of millions of drones could operate without human soldiers' moral agency and ability to refuse illegal orders.
AI Researchers Crack the Delay Problem: New Algorithm Achieves Optimal Performance in Real-World Reinforcement Learning
Researchers have developed a minimax optimal algorithm for reinforcement learning with delayed state observations, achieving provably optimal regret bounds. This breakthrough addresses a fundamental challenge in real-world AI systems where sensors and processing create unavoidable latency.
When AI Agents Disagree: New Research Tests Whether LLMs Can Reach Consensus
New research explores whether LLM-based AI agents can effectively communicate and reach agreement in multi-agent systems. The study reveals surprising patterns in how AI agents negotiate, disagree, and sometimes fail to find common ground.
AI's 'Cheap Wins' in Mathematics Signal a New Era of Human-Machine Collaboration
Fields Medalist Terence Tao reveals AI is solving easier Erdős problems, but the real breakthrough is AI as a tireless junior co-author accelerating mathematical discovery through tedious work automation.
Anthropic's Distillation Allegations Reveal AI's Uncharted Legal Frontier
Anthropic's claims that Chinese AI firms used thousands of fake accounts to extract capabilities from Claude models highlight the legal grey area of model distillation. The incident coincides with Anthropic relaxing its safety policies amid Pentagon pressure.