A hybrid LSTM-Vision Transformer framework enhances prediction of HRRR forecast errors by integrating atmospheric profiles from mesonet profilers. It achieves up to twofold improvement in precipitation error prediction, especially during active planetary boundary layer periods, by better capturing convective error evolution and reducing PBL-related degradation.
An exploratory analysis of 10 vibe-coded C/C++ projects reveals near-zero in-artifact variability, with all decisions resolved at generation time. The paper proposes Variability by Regeneration (VbR), a product-line approach where an LLM acts as a derivation engine, generating tailored binaries from declarative specifications, with a variant dispatcher routing user requests to the correct binary. VbR shifts variability into specifications, not code, offering a new paradigm for SPL engineering.
RODS addresses sample depletion in multi-turn tool-use RL by using reward variance to detect capability boundaries. It synthesizes new data in real time, matching structural complexity of boundary samples, and maintains a dynamic replay buffer that co-evolves with the policy. RODS achieves performance comparable to a 17K-sample offline pipeline with 20x fewer trajectories.
ARIADNE enables dynamic, training-free adapter selection at inference time by using centroids from adapter training data embeddings. It selects the most appropriate adapter based on proximity in latent space, without requiring access to adapter internals or additional training, and achieves 89.7% average selection accuracy across 44 NLP tasks.
The ProductConsistency dataset introduces 87k SFT samples and 869 RL samples to improve product identity preservation in image editing. It includes a benchmark for standardized evaluation and uses a cyclic consistency reward to enforce semantic product identity through caption similarity. Fine-tuning Qwen-Image-Edit-2511 and Flux.1-Kontext-dev shows a 5x reduction in character error rate and improved text rendering and visual quality.
A study finds that leadership styles in multi-agent LLM teams only improve performance when the initial consensus is unreliable, recoverable, and not self-corrected by undirected interaction. Process-level coordination control adds value only under specific conditions predicted by team science, with no single leadership style outperforming others in accuracy across tasks and models.
A new paper proposes a fundamental redesign of the web to prioritize AI agent access, challenging the long-held assumption that humans are the primary web users. It introduces access, economic, and content layer reforms—including agent-identifiable HTTP headers, intent-based subscription models, and a cryptographic provenance system—to enable AI agents as first-class participants, with human supervision and accountability embedded in the architecture.
A study uses SHAP and SSHAP techniques to analyze electricity price drivers in 39 European bidding zones. It finds solar energy has a disproportionate impact on prices, gas remains a dominant factor, and interconnections highlight regional interdependence. The research also builds a synthetic EU-wide market to examine a fully integrated scenario.
Equivariant graph neural networks outperform existing models in predicting optical spectra for materials screening. The adapted GotenNet achieves superior performance, especially in the 0-8 eV range and for static real permittivity prediction, critical for thin-film optics.
PQLRM is a multi-objective reinforcement learning algorithm that combines Pareto Q-Learning with Reward Machines to handle non-Markovian rewards. It converges faster than naive PQL on cross-product MDPs and generates Pareto-optimal policies beyond the capability of QRM.
A new taxonomy classifies LLM agent communication protocols across five dimensions: counterparty, payload, interaction state, discovery mechanism, and schema flexibility. Analysis shows hybrid payloads, session-state persistence, and runtime schema negotiation are common, with decentralized discovery remaining rare. The study predicts short-term convergence toward unified agent-to-agent and agent-to-context protocols, and long-term evolution toward a federated, layered protocol stack.
The Human-AI Coevolution Dynamics Framework (HACD-H) introduces a unified model for long-term human-AI interaction, integrating emotional adaptation, memory, and personality into a self-organizing system. Results show social intelligence emerges through coevolution, with a significant negative correlation between social intelligence and social cognitive energy (r = -0.391, p < 0.001), and progressive energy reduction over time.
OrthoReg introduces orthogonal regularization to prevent neural components from relearning symbolic structures in hybrid dynamical systems. By directly penalizing overlap between symbolic and neural parts, it enables a complementary decomposition where symbolic models capture expressible physics and neural components handle remaining dynamics. On benchmarks with partial library mismatch, OrthoReg improves symbolic recovery and out-of-distribution performance.
AdsMind is a closed-loop multi-agent system that uses machine learning force fields and feedback to correct errors in adsorption configuration searches on catalyst surfaces. It achieves 100% and 98.8% success rates on AA20 and OCD-GMAE62 benchmarks, reduces energy dispersion by 14-fold compared to baselines, and maintains correct adsorption-energy signs in DFT validation, outperforming open-loop LLM agents.
GLM-5.2, a 753B-parameter text-only model from Z.ai, is now the top open weights model on the Artificial Analysis Intelligence Index, outperforming MiniMax-M3, DeepSeek V4 Pro, and Kimi K2.6. It features a 1 million token context window and ranks second on the Code Arena WebDev leaderboard, despite lacking image input capabilities.
llama.cpp has been updated to support downloading and managing models via API. This enables full model lifecycle control through API calls without requiring a user interface.
The Inflect-Nano-v1 model is the second smallest publicly released TTS model after TinyTTS, with 4.63M total parameters. It performs surprisingly well for its size, running locally on low-end devices and offering a baseline for tiny speech synthesis in embedded or offline applications.
A user with a 12GB VRAM GPU asks for model recommendations for general chatting, roleplaying, and coding. They prioritize uncensored models for chat and roleplaying, and have a Ryzen 5600 CPU and 32GB DDR4 RAM.
Lin Junyang's AI lab has closed a funding round valuing the company at $2 billion. The lab is known for its work on the Qwen series of large language models, and the funding round signals continued confidence in open-source AI initiatives.
Claude Code v2.1.181 introduces support for setting config settings via prompt syntax like /config thinking=false, adds sandbox Apple Events support on macOS, and improves streaming, auto-retry, and subagent behavior. It also fixes numerous bugs related to startup, file handling, clipboard, and UI responsiveness across platforms.