Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
Group Relative Policy Optimization (GRPO) is the dominant reinforcement learning algorithm for training reasoning capabilities in large language models, notably adopted by DeepSeek-R1. The recent improvement Dr.
While Large Language Models (LLMs) show great promise for automating unit test generation, recent studies suggest that the quality of generated tests can be negatively impacted when models are prompted with buggy code. This paper presents a new metric to quantitatively measure the "misguidance effect," a phenomenon where buggy code steers LLMs toward generating tests that validate its erroneous behavior rather than expose it.
Tabular foundation models predict the missing column of any spreadsheet zero-shot, the way an LLM completes text — and on the TabArena benchmark they now sit above fully tuned gradient-boosted trees. An introduction to how they work, an independent reproduction of the strongest open one, and a map of where XGBoost still wins.
Enterprise Document Intelligence [Vol. 1 #8quater] - Two angles on the cascade, cost and a validation loop, backed by a real sweep of twenty local models against a hosted flagship The post Loop Engineering for RAG Generation: An LLM Cascade from a Cheap Local Model Up to a Hosted Flagship appeared first on Towards Data Science .
Most AI memory systems keep the newest information—not the most important. Here's how I used the Ebbinghaus forgetting curve to build a better memory engine for LLMs.
arXiv:2607. 20734v1 Announce Type: new Abstract: As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction.
arXiv:2607. 20429v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate diverse human opinions in open-ended tasks such as synthetic surveys, focus group modeling, and public opinion prediction.
arXiv:2607. 20441v1 Announce Type: cross Abstract: Every information ecosystem produces beliefs that shape strategic decisions.
arXiv:2607. 21292v1 Announce Type: new Abstract: We present a structured large-language-model-driven workflow for automated multi-variable control design from dynamic process models.
arXiv:2607. 20444v1 Announce Type: cross Abstract: Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service of a contextually or experimentally induced goal.
arXiv:2607. 21274v1 Announce Type: cross Abstract: We present CUP, a Greek book retrieval benchmark consisting of 868 catalog records and 104 expert-annotated queries with graded relevance judgments.
arXiv:2511. 12997v2 Announce Type: replace Abstract: Multimodal LLM-powered agents have recently demonstrated impressive capabilities in web navigation, enabling agents to complete complex browsing tasks across diverse domains.
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.
arXiv:2607. 21180v1 Announce Type: new Abstract: Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood.
arXiv:2602. 19313v2 Announce Type: replace-cross Abstract: General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, failed, or partially completed behavior.
arXiv:2510. 04019v3 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) represent a promising alternative to autoregressive LLMs; however, the lack of effective post-training techniques, including reinforcement learning (RL), remains a key challenge for dLLMs, especially for downstream applications.
arXiv:2607. 21013v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved impressive performance in multimodal emotion recognition (MER) tasks and lifted MER to a new level that is complex emotion understanding with advanced video understanding abilities and natural language description.
arXiv:2607. 20426v1 Announce Type: cross Abstract: Existing LLM hallucination mitigation methods, including prompt engineering and model optimization, either hardly alter models'internal knowledge or have poor cross-domain generalization.
arXiv:2607. 20435v1 Announce Type: cross Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermarking algorithms directly into their weights.
arXiv:2607. 21577v1 Announce Type: cross Abstract: Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection.