Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
The article explains how startups can select GPT‑6 models and adjust their reasoning effort. It offers guidance on improving prompts and skills, coordinating tools, and preparing production workflows.
The article titled "How to Build a Control Plane for AI Agents" outlines a nine-step process for granting a large language model (LLM) permission to act. It focuses on the practical steps involved in creating a control plane that manages the actions of AI agents. The post was originally published on Towards Data Science.
Propaganda detection is an essential task in natural language processing (NLP), particularly in the context of manipulative political communications. However, identifying specific propaganda technique...
GC--EI--MS is an important technique for analyzing volatile and semivolatile compounds in complex samples. However, conventional methods rely heavily on reference spectral library matching, limiting t...
Large language models (LLMs) are widely used as automatic judges, with validity typically assessed via alignment with human scores. However, aggregate agreement fails to reveal whether humans and LLMs...
Legal systems are increasingly implemented through software, yet scalable methods for translating legal texts into accurate symbolic representations remain underdeveloped. We study this problem throug...
The paper discusses how large language model (LLM) agents can perform epistemic actions—actions that improve the evidence base before making a decision. It identifies three modes of such actions: acquiring missing evidence, transforming available evidence, and probing the system to generate revealing responses. The authors introduce the concept of epistemic scaffolding, referring to interfaces, tools, and environments that enable and audit these actions, arguing that agent design must explicitly address how decision-ready evidence is produced.
HydroJEV is a training‑free, one‑second model that classifies SCADA alarms in water distribution networks into cyberattack, physical fault, normal transient, or faulty sensor. In a benchmark on the C‑Town EPANET network, HydroJEV matched a hand‑written rule tree and outperformed a supervised classifier, especially when few labeled events were available, while being 20‑40 times faster than large language models. When combined with a rule tree gate, it reduced the need for human review by about a third without sacrificing accuracy.
The paper introduces a compact framework that transforms continuous multimodal workplace video into a structured Procedural State Memory called a Work Environment Model (WEM). Using event segmentation theory, it detects segment boundaries based on changes in visual context, location, motion, narration, gaze/object interaction, and optional exocentric workspace evidence, then abstracts each segment into an evidence‑linked event card. These event cards incrementally update the WEM, enabling efficient, auditable documentation and retrieval while respecting on‑premise privacy constraints, and the authors evaluate the system on segmentation quality, memory compression, retrieval fidelity, and long‑horizon QA.
JEV-IDS is an open experimental general network intrusion detection system that uses the Jev System One Model to detect zero‑day intrusions even when labeled data are scarce. The system processes one flow per request and asks the model two questions: a binary attack probability and a finite‑choice traffic category. In tests on a 300‑flow NSL‑KDD pilot split, JEV-IDS achieved an F1‑score of 0.859, precision of 0.941, recall of 0.790, and a novel‑attack recall of 0.838, while being 4.8 times faster and 3.8 times cheaper than GPT‑5.6 Luna and producing 15 times fewer false alarms than a low‑data Random Forest.
The paper introduces PACE, a Provenance-Aware Capability Enforcement system designed to secure tool-using large language model agents by mediating every tool call before execution. PACE employs path confinement to limit influence paths and verifies effects against authenticated authority, distinguishing certified execution contracts from evaluated configurations. Experiments on eight agent‑security benchmarks show that the evaluated configuration reduces attack success in most cases while maintaining near‑native utility.
GeoLatent introduces a geometry‑guided latent structuring approach for 3D reasoning from 2D images, separating position, direction, and global geometry under geometric supervision. It combines Common–Residual Geometry Alignment (CR‑GEO) with routed optimization to prevent latent collapse and to direct visual answer learning through the latents while maintaining full attention. The method achieves state‑of‑the‑art performance on SPAR‑Bench and SPBench, improving geometry effective rank and overall accuracy.
The paper introduces TESS, a scalable data‑selection framework that replaces per‑sample weights with a selection network to improve transferability across datasets and model sizes. It identifies instability in existing meta‑learning for training‑data selection (MTS) due to weight suppression and overreliance on easy features, and proposes a Pointwise Value Matching objective to address these issues. Experiments on large language model safety and instruction tuning show strong transfer from subsets to full corpora and from smaller to larger models.
SPIRAL is a reinforcement‑learning framework that trains language models to employ three inference primitives—sequential reasoning within a trace, parallel sampling of independent traces, and aggregation of those traces—within a single compute pipeline. The model first generates multiple independent chain‑of‑thought traces in parallel, then produces a final aggregation trace conditioned on them, with all components optimized end‑to‑end for the reward of the aggregated response. Experiments on reasoning tasks demonstrate that SPIRAL scales efficiently with inference compute, achieving up to 11× better scaling efficiency and 15% higher performance compared to the GRPO baseline when all three primitives are scaled.
ProtoDCS introduces a robust open‑set test‑time adaptation framework for vision‑language models, addressing the challenge of simultaneously handling covariate‑shifted in‑distribution (csID) and out‑of‑distribution (csOOD) data. It replaces brittle thresholding with a double‑check separation using a probabilistic Gaussian Mixture Model and employs an evidence‑driven adaptation strategy that updates prototypes efficiently, reducing overconfidence and computational cost. Experiments on CIFAR‑10/100‑C and Tiny‑ImageNet‑C show state‑of‑the‑art performance, improving both known‑class accuracy and OOD detection metrics.
JARQ is a plug‑in refinement method for group‑wise post‑training quantizers that alternates a joint least‑squares fit of all group scales with bounded Babai proposals to move many codes together on the current grid. It solves a bilinear box‑constrained mixed‑integer least‑squares problem without backpropagation, preserves the host model’s bit width, groups, zero points, and inference cost, and improves accuracy across Llama‑2, Llama‑3, and Qwen models when paired with RTN, GPTQ, OmniQuant, and AWQ hosts. In practice, JARQ reduces perplexity in 90 of 96 comparisons, cuts three‑bit RTN perplexity by up to 36%, raises mean multiple‑choice accuracy in 23 of 24 configurations, and enhances QEP, QuaRot, and OJBKQ outputs, all within under a minute per 7B block.
JET (Justification Evaluation in Transformer) leverages pretrained language and vision‑language models to choose among a limited set of answers without extra training. It directly evaluates candidate likelihoods, reuses computation across candidates, and runs experiments on desktop CPUs and consumer GPUs to measure decision accuracy and execution cost. Results show high accuracy on the MMLU test set, significant speedups from prefix reuse and cache management, and a 30.8% reduction in process time through input preparation optimizations, all while maintaining unchanged outputs.
The paper introduces Concept-Driven Domain Adaptation (CDDA), a three-stage framework that adapts vision‑language models for concept‑to‑example video retrieval in educational settings. CDDA first structures textual embeddings using textbook and teacher‑handbook concept pairs, then transfers this geometry to documentary visuals with a frozen visual encoder, and finally jointly fine‑tunes both encoders with sparse visual concept supervision. On a middle‑school physics benchmark, CDDA outperforms several multimodal baselines in retrieving concept‑driven moments while preserving concrete image‑text alignment.
arXiv:2610. 01578v1 Announce Type: new Abstract: Why can masked prediction learn useful representations that unmasked reconstruction misses?
The paper introduces OMAF, an Online MARL framework that uses a one-step Transformer-based flow policy to generate coordinated actions efficiently. By replacing costly iterative sampling with a single-step action generation and a joint optimization scheme that couples softmax Q-value estimation with flow policy objectives, OMAF maintains expressive multimodal behavior while improving training speed. Experiments on 10 tasks from MPE and MAMuJoCo demonstrate up to 3.4× higher returns and 10.5× better sample efficiency compared to baseline methods.