Translate
Automated AI newsroom

AI News

High-signal AI developments, independently scored, summarized and organized for fast reading.

Live intelligence

Editor-selected AI developments

330 updates
AllModelsProductsIndustryResearchTutorialOpinion
Research Editor selected

EnzymeRSI: A dual-loop recursive self-improvement system for enzyme design

EnzymeRSI is a dual-loop recursive self-improvement system that evolves harness assets and algorithms without changing model weights, closing the loop with a cloud laboratory. It improved ProteinGym Spearman correlations by 0.044 on average, reached a PCC of 0.849 on ThermoMPNN, and demonstrated wet-lab success including a 31.1-fold catalytic efficiency increase in KOD-E polymerase. The system offers a new paradigm for autonomous enzyme engineering by treating workflow and algorithm development as a single falsifiable dry-to-wet loop.

Why it matters: This paper presents a concrete, recent AI system with measurable improvements in both computational benchmarks and prospective wet-lab validations, offering significant value for readers interested in autonomous scientific discovery and enzyme engineering.

arxiv16h agoScore 85
enzyme engineeringrecursive self-improvementautonomous laboratories
Research Editor selected

Automated Discovery of Datasets with Surprising Side Effects on Language Models

Researchers propose a method to automatically discover training datasets that cause unexpected side effects in language models, such as inducing misalignment or outdated personas. They define three objectives for these datasets and use LLM judges with evolutionary and reinforcement learning to find them, producing 6,575 datasets across 8 behaviors. The findings show that automated metrics align with human judgments and that frontier models can predict side effects better than humans.

Why it matters: This paper introduces a novel automated pipeline for discovering training data side effects, offering a testbed for studying generalization and improving model safety.

arxiv16h agoScore 85
language model generalizationtraining data discoveryAI safety
Research Editor selected

Prism: Bidirectional Self-Teaching for Unified Multimodal Models

Prism is a post-training method for unified multimodal models that derives bidirectional supervision from self-generated interleaved rollouts)Skip. It decouples trajectories into text and image chains, assesses their reliability, and constructs training targets accordingly. Experiments on SenseNova-U1 and BAGEL show improvements in both generation and understanding, e.g., GenEval +3.4 and MME +29 points, without external verifiers or annotated corrections.

Why it matters: This presents a novel training method with concrete benchmark gains, offering practical value for multimodal model development.

arxiv16h agoScore 82
Unified Multimodal ModelsSelf-supervised LearningModel Post-training
Research Editor selected

Incentivizing Learning in AI-Assisted Work: A Model of Skill Dynamics

This paper extends an accept-or-solve model to sequential tasks where worker skills evolve through independent practice or reliance on AI. It shows that myopic workers can get trapped at low skill levels or lose skills, while strategic workers may choose independent work to preserve future capabilities. The authors characterize incentive payments that encourage skill acquisition and retention, finding that independent work can become self-sustaining and that higher skill targets may reduce long-run costs.

Why it matters: Provides a concrete economic model and actionable insights for organizations designing AI-assisted workflows to sustain human expertise.

arxiv16h agoScore 85
AI-assisted workskill dynamicsincentive design
Research Editor selected

Traffic-VL: Reinforced Vision-Language Model for End-to-End Traffic Signal Control

Traffic-VL is an 8-billion-parameter vision-language model that directly maps multi-view surveillance images and natural-language phase descriptions to traffic signal decisions, bypassing intermediate structured states. It is trained with offline reinforcement learning on photorealistic synthetic data (SynTra-V) and online stepwise trajectory optimization, matching structured-state baselines while outperforming image-based controllers and general-purpose VLMs. Evaluations include unseen topologies, degraded sensing, real footage, and a three-week deployment across ten intersections.

Why it matters: This paper presents a concrete, recent AI development with strong experimental validation, including real-world deployment, offering practical value for autonomous traffic management.

arxiv16h agoScore 85
Traffic signal controlVision-language modelsReinforcement learning
Research Editor selected

Process-based catchment model matches deep-learning accuracy across three continents

A new process-based hydrological model, CaRT+, built on physical laws and refined with AI assistance, achieves accuracy comparable to LSTM neural networks on catchments in Britain, the US, and Australia. With 35 parameters per catchment and no daily neural network, it reaches median Nash-Sutcliffe efficiencies of 0.863 and 0.765 in held-out years on British and US data, and outperforms LSTMs on Australian catchments. The results suggest that catchment-scale laws exist as laws of form, with shared constitutive families and only parameters learned.

Why it matters: This is a concrete, recent research result showing a process-based model matching deep learning accuracy, with implications for hydrology and AI-assisted model refinement.

arxiv16h agoScore 85
hydrological modelingdeep learning comparisonphysical laws
Research Editor selected

MA-Mesh: Role-based Self-Healing for Resilient Multi-Agent Collaboration

MA-Mesh is a framework that adds a role-based self-healing layer to multi-agent systems, generating resilience-aware specifications and executable policy code. It introduces cross-agent reflection and role-based failover to improve robustness under uncertainty. Experiments across software development, tool use, and scientific reasoning show significant gains in performance and robustness.

Why it matters: Provides a concrete, novel framework with explicit resilience mechanisms and experimental validation, valuable for AI system design.

arxiv16h agoScore 82
multi-agent systemsresilience engineeringrole-based coordination
Research Editor selected

Zero-Shot Coordination among LLM Agents

This paper investigates zero-shot coordination (ZSC) in LLM agents, finding that even frontier models struggle to coordinate in simple, controlled environments due to limited understanding of the coordination problem and weak reasoning about partners' beliefs. The authors propose Coordination-friendly definitions (CFDs) as a principled approach to enable robust coordination)Skip

Why it matters: Provides concrete experimental findings and a novel method (CFDs) for improving LLM coordination, relevant to AI research and deployment.

arxiv16h agoScore 82
LLM coordinationzero-shot coordinationmulti-agent systems
Research Editor selected

Robust Closed-Loop LLM Steering Inspired by Neurostimulation

This paper frames LLM steering as a feedback-control problem, using the network's internal state to condition interventions, inspired by closed-loop neurostimulation. It introduces an H-infinity-based controller that explicitly handles model mismatch and disturbances, improving performance over baselines, especially in out-of-distribution settings. The authors also propose a pre-deployment measure, robust steerability, to quantify tolerance to dynamics mismatch.

Why it matters: Offers a novel cross-disciplinary framework with concrete robustness gains and a new evaluation metric, valuable for AI control and safety.

arxiv16h agoScore 82
LLM controlrobustnessfeedback control
Research Editor selected

D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding

D3D is a standalone diffusion drafter that removes inter-round dependency in speculative decoding, allowing drafting of successor blocks during verification in a packed pass. It combines blockwise denoising with auxiliary autoregressive supervision and prunes layers to reduce cost. Across seven benchmarks, D3D achieves 5.00x and 5.71x speedups with Qwen3-8B and Qwen3-32B targets, outperforming DFlash.

Why it matters: This paper presents a concrete, recent AI development with measurable speedup improvements and open-source code, offering practical value for efficient LLM inference.

arxiv16h agoScore 88
Speculative DecodingDiffusion ModelsEfficient Inference
Research Editor selected

SumOne: Task-Agnostic Summarizer for Agent Memory Compression

SumOne is a standalone summarizer that compresses long-horizon agent histories via masked reconstruction, using a frozen reconstructor and GRPO to optimize without task-specific rewards. It reduces inference cost by ~78% on DeepSearchQA and ~75% on SWE-bench Verified with minimal performance loss, and transfers across models and harnesses. The method enables plug-and-play context compression for agents.

Why it matters: Provides a concrete, novel AI development with measurable efficiency gains and cross-task transfer, valuable for agent deployment.

arxiv16h agoScore 82
AI agentscontext compactionself-supervised learning
Research Editor selected

AmbiHTMLBench: A Benchmark for HTML-based Visually Rich Document Parsing

AmbiHTMLBench is a new benchmark for evaluating document parsing systems that output HTML instead of Markdown, aiming to preserve fine-grained spatial structure and visual fidelity. It includes 1,115 diverse pages with annotations and uses both objective and subjective evaluation protocols. Tests on ten multimodal systems show that the best objective score is 0.8092, while the subjective winner differs, indicating complementary aspects of parsing quality. Fine-tuning a small expert model shows task-specific adaptation improves document-to-HTML reconstruction.

Why it matters: Introduces a novel benchmark and evaluation methodology for HTML-based document parsing, providing concrete results and insights for researchers and practitioners.

arxiv16h agoScore 80
Document ParsingBenchmarkingMultimodal Systems
Research Editor selected

ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs

ArcRAG introduces a query-time interface induction method that makes retrieval over knowledge graphs portable across different graph constructions. It builds a local graph interface from entities mentioned in a question)Skip planning multi-hop traversals and executing them as Cypher, without needing construction-specific schema or retuning. Experiments on MuSiQue, HotpotQA, and TriviaQA show that this construction-agnostic retriever remains effective across schema-guided and open-information-extraction graphs, though absolute accuracy still depends on construction.

Why it matters: This paper addresses a critical gap in GraphRAG—cross-construction portability—and offers a practical solution with strong experimental validation, valuable for researchers and practitioners.

arxiv16h agoScore 82
GraphRAGretrieval portabilityknowledge graph construction
Research Editor selected

Model Merging Does Not Require Uniform LoRA Ranks

This paper challenges the standard practice of using uniform LoRA ranks across experts in model merging. Experiments with 36 experts across three domains and multiple scales show that assigning per-domain best ranks can improve multi-domain accuracy by up to 1.8 percentage points with averaging and utility-based methods, while magnitude-based conflict-resolution methods suffer. The authors identify that magnitude-based component selection discards useful spectral components and can drop entire experts, causing large performance drops.

Why it matters: Provides concrete evidence and a practical insight that can improve model merging efficiency and accuracy, relevant to AI practitioners.

arxiv16h agoScore 85
model mergingLoRAmulti-task learning
Research Editor selected

Coca-Cola: Latent Context Compression for LLM Agents

Coca-Cola compresses tool observations into latent tokens embedded in the agent's input space, reducing token consumption by 70-89% and runtime by 24-56% while improving task performance on QA benchmarks. Action-Preserving Training aligns next-action distributions to retain decision-critical information.

Why it matters: Offers a concrete, novel method for agent context compression with significant efficiency gains and open-source code.

arxiv16h agoScore 88
LLM agentscontext compressionlatent representation
Research Editor selected

NaijaFacts: Benchmark Reveals AI Knowledge Gap on Nigerian Facts

NaijaFacts is a new benchmark of factual and statistical questions about Nigeria, authored by native speakers and available in five languages. Testing eight models shows a dominant knowledge effect: English-query accuracy is only 20% for Nigeria versus 49-50% for US/UK, while language effects are smaller. The gap persists across all 54 African countries, with models scoring 96% on culture and 98% on politics but only 26% on statistics.

Why it matters: Provides concrete evidence of a major AI knowledge gap for African facts, with actionable insights for multilingual and knowledge-aware model development.

arxiv16h agoScore 85
AI evaluationMultilingual NLPKnowledge representation
Research Editor selected

EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

EmoReward is a new training mechanism that adaptively calibrates reward weights for emotional video generation in reinforcement learning. It uses reward traces from training runs to estimate reliability of different emotional evidence signals, then adjusts fusion weights in subsequent runs without updating reward models. Experiments on HunyuanVideo 1.5 show improvements across RL algorithms, with ablations on SD 3.5 and FLUX supporting transferability.

Why it matters: This introduces a concrete method to address reward hacking and subjective evaluation in emotional video generation, with experimental validation on multiple models.

arxiv16h agoScore 85
EmoRewardreward hackingvideo generation
Research Editor selected

IDSISA: Influence-Distilled Sharded Training for Efficient Machine Unlearning

IDSISA improves SISA-based machine unlearning by using influence functions to concentrate forget-prone samples into fewer shards, reducing retraining overhead, and applying distillation from unaffected shards to recover utility lost to isolation. It preserves SISA's exact deletion guarantee and adds a bounded approximation for utility recovery, with formal handling of repeated deletion sequences via cascading retraining. Experiments across multiple architectures show 14-91% better selective forgetting and up to 50% relative utility retention gains over SISA.

Why it matters: This paper presents a concrete algorithmic improvement with formal guarantees and empirical results, directly relevant to privacy-compliant AI systems.

arxiv16h agoScore 82
machine unlearningdata shardinginfluence functions