Skip to content

Research separate from news

What could become important next

A preprint is a signal, not a finished product or an independently confirmed result. We therefore track research papers separately and show the actual state of supporting evidence for each one.

1381 published research events

Latest work

A significant claim from a single source is published only after further confirmation.

Research only one source so far

Study presents FlexRouter for selecting mutually complementary LLM models

The study presents FlexRouter, which selects LLM models based on their capabilities and mutual complementarity. It determines the number of models dynamically. According to the authors, in RouterEval tests it achieves a higher probability of at least one correct answer and lower redundancy than the compared methods.

arXiv cs.LG (Machine Learning) Original source ↗
Research only one source so far

Study presents the AIMS framework for transferring models from simulations to wireless networks

The AIMS framework uses two agents to coordinate the creation of simulated data and model training for multi-modal ISAC. The authors report better vehicle detection and beam prediction on the DeepSense 6G dataset compared to selected baseline methods; the abstract does not state the magnitude of the improvement.

arXiv cs.AI (Artificial Intelligence) Original source ↗
Research only one source so far

Study uses AI and acoustics to examine two Etruscan tombs

Researchers combined AI, acoustic and visual techniques in studying two Etruscan tombs from the 5th century BC. The results suggest that sound and lighting enhanced the impact of the paintings on visitors. The specific AI method is missing from the available excerpt.

The Conversation — Artificial Intelligence Original source ↗
Research only one source so far

The KUPAS MASTER study examines the conversion of professional experience into AI agent skills

The study presents the KUPAS MASTER platform for converting professional experience into AI agent skills. It processed 1 576 files from 20 experts. In the evaluation, the agent achieved a score of 89.58, compared to 79.75 when using RAG over the original source materials and 70.63 for the base model.

arXiv cs.AI (Artificial Intelligence) Original source ↗
Research only one source so far

DASA method explores LLM adaptation without human-readable text

The study presents the DASA method, which uses synthetic input representations for LLM adaptation. According to the authors, it achieves comparable or better results than original text data on six models with 1–32 billion parameters. Synthesis is 3.6–4.9× faster than the GRADMM method.

arXiv cs.AI (Artificial Intelligence) Original source ↗
Research only one source so far

Study introduces SCLATE for training and evaluating AI agents

The SCLATE study compares 10 agent configurations across 10 models and 7 task sets. Added memory did not reliably improve performance. According to the authors, fine-tuning the Qwen3.5-4B model increased the success rate on the SWE-bench Verified set by 16.7 percentage points.

Apple Machine Learning Research Original source ↗