Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
Capybala released a SKILL.md workflow that drives headless Blender through a Stage A → B → C process — planning the component list, building against calibrated camera, lighting, and material presets, then self-reviewing …
A developer tested CrewAI 1.15.21 with three agents — an Analyst and Writer on Qwen 3 235B via OpenRouter and an Editor on Anthropic's Claude Opus 4.8 — and found that apparent agent-to-agent conversation is actually too…
GoTo, the Indonesian technology group and parent company of Gojek, is narrowing its AI investments to applications that improve customer conversion or cut costs, ahead of a wider rollout in 2027, president director and g…
A new research paper proposes learning to select poison sets rather than sampling them at random, aiming to strengthen backdoor poisoning attacks on large language models. Backdoor poisoning attacks add poisoned examples…
Injecting tool-derived context directly into grep output eliminated the tool-adoption problem for coding agents, with all 99 files surfaced by the annotations opened and 92 receiving patches, according to a blog post by …
LangSmith, a monitoring and observability platform built by the creators of LangChain and LangGraph, traces AI applications by logging every input and output across each step of a pipeline, according to a technical deep …
A study comparing traditional machine learning models against LLM-generated rule-based systems for heart disease prediction on the UCI Heart Disease dataset found that traditional models consistently outperformed the LLM…
A new arXiv paper (2609.13201v1) models AI-generated text and images as anomalies linked to main data points and derives bounds on the minimum size of a strongly dissimilar decomposition of random datasets using redundan…
A controlled study across several versions of two major tabular foundation model (TFM) families found that feature engineering gains are concentrated in earlier model generations and become negligible for the strongest m…
A new analysis method called Elo-per-token measures how large language model agents allocate test-time compute as they revise solutions, use tools, explore alternatives, and decide when to stop, addressing the difficulty…
A training-free, CPU-only lexical prompt-compression pipeline reduced prompt tokens by a mean of 40.3% (sigma = 9.2) while holding BERTScore-F1 at 0.876 against original-prompt output, according to an arXiv paper (2609.1…
Researchers introduced TestHallVQA, a multi-image visual question answering benchmark built from scientific exams that combines document-level scale with human-examination difficulty, according to the arXiv paper 2609.13…
A new arXiv paper, RFCLLM, evaluates how well large language models reason about network protocol state machines, testing 16 protocols across 4 tasks and 1482 task queries. The study compares each LLM's implicit finite-s…
A maxillofacial cone beam CT report generation system scored 0.4122 against a composite objective that weights 80% on large language model factual entailment and 20% on lexical overlap, versus 0.2909 for a report selecte…
A new arXiv paper (2609.13454v1) introduces a paired benchmark of 171 PubMed Central Open Access case reports — 40 sepsis and 131 GLP-1/diabetes cases — to measure hindsight bias in clinical temporal reasoning by large l…
Researchers identified Harmfulness Propagation Dynamics (HPD), a cross-layer signature in which the projection of the last-token hidden state onto a learned harm direction rises monotonically with transformer depth for h…
Researchers proposed ModelLog, a declarative probabilistic framework for pre-training evaluation of large language models that specifies evaluation targets as symbolic constraints over token-level predictions, according …
Researchers built pseudo-references for the WMT26 General MT task's 10 reference-free language pairs by translating 3,277 official documents with seven models across up to five prompt conditions, producing 26 system-prom…
A new arXiv paper (2609.13581v1) presents an evidence-driven alignment framework for hospital discharge summarization that treats provenance as a first-class constraint, using semantic graphs and deep learning models to …
The University of Melbourne's submission to the WMT 2026 Creole Language Translation Shared Task reports that its machine translation models for Pacific creoles Tok Pisin, Bislama, and Solomon Pijin beat open model basel…