The latest AI news, launches, models, companies and research — collected from official sources, research feeds and reporting, grouped into stories and ranked by the BharatHunt Trend Score.
Ingestion is behind — last completed run was 19 hours ago.
News ingestion is temporarily unavailable.
The pipeline has not completed a run recently, so what is below may be behind. Nothing here is ever filled in with placeholder news.
387 stories
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents. It centres on Benchmarks, and also names Inference. Reported by arXiv. Bharat Hunt files it under AI Models and AI Research — the section covering a new or updated model, its capabilities, benchmarks or availability.
Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency. It centres on Reasoning Models, and also names Inference and Fine-tuning. Reported by arXiv. Bharat Hunt files it under AI Models and AI Coding — the section covering a new or updated model, its capabilities, benchmarks or availability.
Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs. It centres on Reasoning Models, and also names Benchmarks and DeepSeek. Reported by arXiv. Bharat Hunt files it under AI Research and AI Models — the section covering papers, benchmarks, evaluations, interpretability and safety results.
Auditable Long-Term Memory: A Deterministic Retrieval Chain Measured at 479/475 of 500 on LongMemEval-S. It centres on Claude, and also names GPT and Grok. Reported by arXiv. Bharat Hunt files it under AI Models and AI Agents — the section covering a new or updated model, its capabilities, benchmarks or availability.
Africa-Papers: A 10-Billion-Token Multi-Domain Academic Corpus for African Foundation Language Models. It centres on Hugging Face, and also names Benchmarks. Reported by arXiv. Bharat Hunt files it under AI Models and AI Funding — the section covering a new or updated model, its capabilities, benchmarks or availability.
Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs. It centres on Reasoning Models, and also names Apple. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability.
Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries. The story centres on Benchmarks. Reported by arXiv. Bharat Hunt files it under AI Agents and AI Models — the section covering autonomous and tool-using systems, agent frameworks, MCP and orchestration.
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries. It centres on Inference, and also names Claude Code. Reported by arXiv. Bharat Hunt files it under AI Models and AI Agents — the section covering a new or updated model, its capabilities, benchmarks or availability.
ViSTA: A Simple Bridge Extends Visual Alignment to Clinical Time-Series Understanding in Multimodal LLMs. It centres on AI Safety, and also names Multimodal and GPT. Reported by arXiv. Bharat Hunt files it under AI Models and AI Research — the section covering a new or updated model, its capabilities, benchmarks or availability.
From Triage to Impact: A Multi-Hop Reasoning Benchmark for Explainable Persian Hate Speech. It centres on Benchmarks, and also names Inference and GitHub. Reported by arXiv. Bharat Hunt files it under AI Research and AI Models — the section covering papers, benchmarks, evaluations, interpretability and safety results.
Aligning MLLMs with the Latent Structure of Human Cognition via Behavior-Derived Semantic Dimensions. It centres on Multimodal, and also names Benchmarks and AI Safety. Reported by arXiv. Bharat Hunt files it under AI Models and AI Research — the section covering a new or updated model, its capabilities, benchmarks or availability.
NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding. Reported by arXiv. Bharat Hunt files it under AI Hardware and AI Models — the section covering chips, accelerators, data centres, on-device inference and supply. Open the original report for the full detail.
Bharat Hunt links to original reporting and does not republish it. Headlines and links belong to their publishers; summaries and the trend ranking are ours. All AI stories
Our own 0-100 ranking, not an industry metric and not anyone else’s “trending” number. It combines how recently a story was covered (32%), how many independent publications covered it (28%), how fast that coverage is arriving right now (20%), how reliable those sources are (12%) and how many people opened the story (8%).
A story we cannot date carries no score at all rather than a made-up one, so some cards show no badge. Summaries are written by Bharat Hunt from the headline and the coverage — the original article is always the source of truth, and every link goes to the publisher.