Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
AI tutoring startup Aristotle argues that most AI tutors are generic chatbots that fail students because they hand over answers rather than guide reasoning, and says its voice-first system is built on the ICAP engagement…
Bridgewater Associates co-CIO Greg Jensen said on Bloomberg's Odd Lots podcast on September 11, 2026 that there is a 30 to 60 percent chance AI causes a major financial or fatal disaster within two years, warning that "u…
A developer has published a set of conversational reasoning patterns designed to make other agentic coding assistants reason in an "Opus style." The approach prescribes specific verbal markers for flagging caveats, ackno…
Researchers introduced the KuaiRP series of role-playing models in a technical report, using a multi-stage training pipeline to inject deep domain knowledge without losing general agent capabilities. The pipeline combine…
A meta-agent variant achieved the highest Avg@3 reward on five of six heterogeneous benchmarks in a study of task-agnostic environment preprocessing, according to an arXiv paper (2609.10824v1). The research formalizes a …
A tail-risk-aware turn release scheduling method for agentic LLM workflows reduces the P95 of workflow flow time under contention by up to 3.50x, according to an arXiv paper (2609.10964v1). The method, which uses a mean-…
A new arXiv paper (2609.10992v1) analyzes the privacy-utility trade-off in Large Language Model interactions and introduces an intent-driven local protection framework built on a distilled lightweight model, Veilmind-4B.…
A new arXiv paper (2609.11061v1) proposes belief-shift branching, a fork-placement method for tree-structured reinforcement learning with verifiable rewards that forks a chain just before the step where the model's conse…
Researchers introduced Mosaic, a training-free framework that formulates GraphRAG retrieval as a per-query control problem, with an LLM analyzer converting query-specific evidence requirements into a bounded policy over …
A study posted to arXiv (2609.11452v1) introduces RouteRepair, an instance-level failure diagnosis and targeted repair method for LLM-based automated heuristic design in routing optimization. On the traveling salesman pr…
Researchers introduced ActMap, a white-box representation that compresses a large language model's generation-time hidden-state trajectory into a fixed 12 × 32 × 128 tensor occupying 96 KiB, enabling single-pass uncertai…
A new benchmark called NovGauge, built from 619 paper pairs and 50 multi-paper sets drawn from ICLR reviewer overlap claims and survey co-citations, finds that large language models remain unreliable at assessing scienti…
A three-stage agentic pipeline combining static scanning, LLM-driven CWE reasoning, and autonomous exploit verification in isolated Docker containers found that 14.53% of statically clean Python samples were exploitable …
A new arXiv paper (2609.11199v1) presents an AI-driven, culturally sensitive stress detection and wellness support system for Pakistani university students, built on a Random Forest model trained on 1,100 validated stude…
COBRA-Skills, a framework introduced in arXiv paper 2609.11682v1, formulates LLM agent skill optimization as budgeted sequential optimization over a dynamically evolving candidate space, coupling contextual-bandit-guided…
Researchers released Benchmark Radar, a living database and search engine for AI benchmarks that catalogs 1,283 source records drawn from 4 benchmark catalogs and 12,916 numeric observations on 790 records. The system dr…
A new arXiv paper (2609.11709v1) proposes Bayesian backward reasoning as a label-free anchor for multi-agent collective decision-making, using Jensen-Shannon divergence to rank LLM agents by cross-path consistency. Evalu…
A multi-agent AI system called Agentic Share-of-Search (ASoS) automates competitive visibility measurement and root-cause diagnosis in LLM-mediated e-commerce, according to an arXiv cs.AI paper by Spandan Ghose Chowdhury…
A randomized controlled study of 100 medical students found that a scaffolding-oriented multi-agent LLM AI Standardized Patient (AI-SP) platform improved final examination scores over a control condition using structured…
A study of approximately 119,000 archaeology abstracts from Scopus published between 2010 and 2025 found only a small but credible shift in computational method use after 2023, with overall methodological diversity incre…