Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
A new study finds that online web agents augmented with memory, workflow, or skill modules often fail to outperform a token-matched vanilla baseline under a fixed inference budget. Testing across three models and multipl…
A new empirical study systematically compares tokenizers for multilingual large language models across 11 Southeast Asian languages, finding that Parity-aware BPE achieves the best balance of compression efficiency and c…
Researchers propose ASAG, a training-free method that monitors attention distributions to detect when a reasoning model has reached a conclusion, stopping generation early. Applied to DeepSeek-R1-Distill and Qwen3 models…
Researchers introduced Ling-2.6 and Ring-2.6, a family of models designed for efficient and scalable agentic intelligence at trillion-parameter scale. Ling-2.6 optimizes for instant response generation, while Ring-2.6 fo…
Researchers introduced PanicCognitivePath (PCP), a framework combining cognitive graphs with large language models to predict panic emotional arousal timing before manifestation. PCP uses a Psychological Safety Distance …
Researchers introduced AgentViSS, a benchmark for evaluating visual social intelligence in multimodal agents, featuring 240 scenarios and four role-level tasks. Tests on seven multimodal large language models revealed th…
Researchers propose QPILOTS, a method that steers flow-matching and diffusion policies at inference time by projecting noisy intermediate states to clean action estimates for critic gradient computation. QPILOTS achieves…
Researchers propose GRASP, a method for multi-source transfer learning that achieves 93.5% mean accuracy across benchmarks while using constant memory, compared to 71.7% for ensemble methods. GRASP sequentially merges so…
Researchers reformulated the autoresearch pattern as a stateful ReAct agent using LangGraph, achieving 90% fewer tokens on hyperparameter tuning and 52% fewer on code optimization compared to stateless designs. The state…
Researchers introduced FASTMIX, a framework that automates data mixture optimization for training large models by reformulating mixture selection as a bilevel optimization problem and using gradient descent to jointly op…
Researchers trained a two-layer transformer encoder to classify rational elliptic curves by rank, achieving over 99% accuracy. The model learned the Mestre-Nagao heuristic from data alone, with input weights matching the…
Researchers introduced a temporal difference (TD) objective for diffusion models that enforces cross-time consistency along the denoising trajectory, improving sample quality especially with few sampling steps. The metho…
Researchers introduced AdaNAGED, a zero-order parameter-free optimization method for LMO-based fine-tuning of large language models, addressing memory overhead and sensitivity to hyperparameters. The method unifies gradi…
A developer used the low-code tool n8n to build self-hosted AI-powered automation workflows, prioritizing data privacy and control. By deploying n8n with Docker Compose, PostgreSQL, and Redis, the developer created a fle…
Brazilian public sector AI project Rio 3.5 Open accidentally released an incomplete checkpoint, which was later removed. The model, built on Alibaba's Qwen 3.5 and Nex-AGI's Nex-N2 Pro, was not a foundational model but a…
QuantaMind has developed a platform that addresses fragmentation in local LLM tool-calling by using a text-prompt structure as a universal baseline and providing a side-by-side native function-calling view. This allows d…
A developer shared a set of agent skills used for development, including skills for interviewing users about plans, creating PRDs, breaking down plans into GitHub issues, implementing tasks with TDD, and analyzing codeba…
OpenAI's 'Practical Guide to Building Agents' has sparked a debate with LangChain CEO Harrison Chase, who called it 'misguided' and published a detailed rebuttal. The conflict highlights a core tension in AI engineering …
The US administration suspended access to Anthropic's most powerful Fable series models, exposing Europe's vulnerability from relying on foreign AI infrastructure. European labs have fallen behind, with Mistral lagging s…
A developer released Pi, a coding agent that runs entirely on a local machine without API keys or cloud dependencies. Pi works with a local llama.cpp server hosting Google Gemma 4 models, enabling offline AI-assisted cod…