News index for Wednesday, October 28, 2026

3021 stories from 525 sources, most popular first. Showing 3001–3021. Other days: Oct 27 Oct 26

3001. DateStorySourcePop. / Similar
3002. Oct 28, 00:00Can LLMs Reliably Grade Olympiad Proofs? A Study of Mathematical Verification with LLMsarxiv.org6 / 0AI & Data Science · Artificial Intelligence
3003. Oct 28, 00:00Batching the Reflective Optimization Loop: Parallel Proposals Make GEPA Faster and Betterarxiv.org6 / 0Computing & Software Development · Technology & Consumer Electronics
3004. Oct 28, 00:00Dependency Graphs of Mathematical Arguments: Representation, Structural Measurement, and Proof Reviewarxiv.org6 / 0AI & Data Science · Artificial Intelligence
3005. Oct 28, 00:00An Incremental Knowledge-Graph Learner Digital Twin for Evidence-Grounded Early Warningarxiv.org6 / 0Industry & Manufacturing · Business & Finance
3006. Oct 28, 00:00Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mindarxiv.org6 / 0AI & Data Science · Artificial Intelligence
3007. Oct 28, 00:00When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvementarxiv.org6 / 0Wellness & Mindfulness · Wellness, Fitness & Nutrition
3008. Oct 28, 00:00Conservative Policy Iteration For Zero-Sum POSGsarxiv.org6 / 0
3009. Oct 28, 00:00Evolving Agent Teamsarxiv.org6 / 0Consumer Electronics & Hardware · Technology & Consumer Electronics
3010. Oct 28, 00:00GUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agentsarxiv.org6 / 0AI & Data Science · Artificial Intelligence
3011. Oct 28, 00:00RubricAtlas: Mining Type-Level Rubrics from Expert Reports to Evaluate Deep Research Agentsarxiv.org6 / 0AI & Data Science · Artificial Intelligence
3012. Oct 28, 00:00Noise Steering: Exploiting Wake Steering and Acoustic Directivity for Noise-Constrained Wind Farm Control via Reinforcement Learningarxiv.org6 / 0Solar, Wind & Renewables · Energy & Climate Tech
3013. Oct 28, 00:00Natural Hard-Negative Mining from Positives for Instruction-Following Retrievalarxiv.org6 / 0AI & Data Science · Artificial Intelligence
3014. Oct 28, 00:00Vision-Language Agents Can Learn in Their Own Latent Worldsarxiv.org6 / 0Machine Learning Research · Artificial Intelligence
3015. Oct 28, 00:00Do bots feel bad? Assessing empirical evidence for functional valence in LLMsarxiv.org6 / 0Brain & Neuroscience · Discovery & Research
3016. Oct 28, 00:00Proactive Memory for Event-Driven LLM Agentsarxiv.org6 / 0Cloud, DevOps & Infrastructure · Technology & Consumer Electronics
3017. Oct 28, 00:00AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operationsarxiv.org6 / 0AI & Data Science · Artificial Intelligence
3018. Oct 28, 00:00SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generationarxiv.org6 / 0Machine Learning Research · Artificial Intelligence
3019. Oct 28, 00:00Guided-RLVR: Guided Exploration in Reinforcement Learning with Verifiable Rewardsarxiv.org6 / 0Machine Learning Research · Artificial Intelligence
3020. Oct 28, 00:00AI-Assisted Discovery of CNOT Decompositions for Quantum Permutations on Constrained Topologiesarxiv.org6 / 0Physics & Chemistry · Science
3021. Oct 28, 00:00Correctness Conditioning as Selection in Chain-of-Thought Faithfulness Evaluationarxiv.org6 / 0Generative AI Tools & Use · Artificial Intelligence
3022. Oct 28, 00:00OpenGray: a benchmark for evaluating the decisions of radiotherapy planning agentsarxiv.org6 / 0AI & Data Science · Artificial Intelligence