Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
Researchers developed Metric Match, a subset selection method that estimates LLM judge reliability from limited human annotations. The method achieved a win-rate of 0.838 against random selection across 15 datasets, redu…
Researchers introduced an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries. The system uses three agents—Guardrail, General-QA, and Recommender…
Researchers applied the Verifiable Growing Physical Transformer with Recursive Self-Improvement (VGPT-RSI) to produce formally verified partial progress on problems adjacent to the Riemann Hypothesis, including a finite …
Researchers introduced IRTS-ToolBench, a benchmark of 1,700 questions across 10 task types and 13 domains, to evaluate large language models and AI agents on irregular time series question answering. The benchmark addres…
Researchers propose CONCORD, an asynchronous sparse aggregation framework for device-cloud retrieval-augmented generation under document isolation, which improves throughput by up to 2.15x and reduces communication by ov…
Researchers propose CogGuard, a proactive-warning framework for edge intelligent services that uses LLMs for offline profile construction and SLMs for online score prediction. The framework reduces profile construction t…
Researchers propose Visual-Seeker, a multimodal deep search agent that actively reasons over visual details to perform multi-hop, cross-modal search. The agent achieves state-of-the-art results on five benchmarks, surpas…
Researchers introduced Mask-Proof, an LLM-based automated data curation pipeline that converts mathematical proofs into checkable masked-step tasks, creating the Mask-ProofBench benchmark with 292 problems. Testing 17 mo…
Researchers at UC Riverside introduced the first robustness study for proof autoformalization in Lean 4, testing seven LLM-based models on perturbed informal proofs. All models showed sensitivity to global paraphrasing a…
Researchers at arXiv propose Telegraph English, a readable symbolic format for context compression that rewrites retrieved passages into structured entity-relation statements. In experiments on multi-hop QA datasets, it …
Researchers propose AC-GPT, a modification to causal Transformers that enables evaluating and sampling from arbitrary conditionals in a single forward pass without degrading standard left-to-right performance. The method…
Researchers introduced CoRA, a GRPO-based reinforcement learning framework that aligns LLM confidence with rationale quality in chain-of-thought reasoning. Across MedQA, MathQA, and OpenBookQA, CoRA reduced confidence-ra…
NVIDIA released Nemotron 3 Ultra, a 550B-parameter hybrid Mamba-Transformer model with 55B active parameters, achieving up to 6x higher inference throughput than state-of-the-art LLMs while maintaining accuracy. The mode…
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…