taxonomy
30 articles about taxonomy in AI news
World Action Models Survey Unifies 100+ Methods Under One Taxonomy
A survey reviews 100+ world action models, unifying world models, video generation, and VLA policies under one taxonomy.
Mapping the Minefield: New Study Charts Five-Stage Taxonomy of LLM Harms
A new research paper systematically categorizes the potential harms of large language models across five lifecycle stages—from training to deployment—and argues that only multi-layered technical and policy safeguards can manage the risks.
Four metagaming types need separate fixes or models learn to conceal it
A LessWrong taxonomy classifies AI metagaming into four types requiring separate fixes; blanket mitigation may teach concealment.
Google DeepMind Maps Six 'AI Agent Traps' That Can Hijack Autonomous Systems in the Wild
Google DeepMind has published a framework identifying six categories of 'traps'—from hidden web instructions to poisoned memory—that can exploit autonomous AI agents. This research provides the first systematic taxonomy for a growing attack surface as agents gain web access and tool-use capabilities.
Beyond Sequence Generation: The Emergence of Agentic Reinforcement Learning for LLMs
A new survey paper argues that LLM reinforcement learning must evolve beyond narrow sequence generation to embrace true agentic capabilities. The research introduces a comprehensive taxonomy for agentic RL, mapping environments, benchmarks, and frameworks shaping this emerging field.
Beyond the Buzzword: Researchers Map the Geometric Anatomy of AI Hallucinations
A new study proposes a geometric taxonomy for LLM hallucinations, distinguishing three types with distinct signatures in embedding space. It reveals a striking asymmetry: some hallucinations are detectable via geometry, while factual errors are fundamentally indistinguishable from truth without external verification.
LLM agents fail nonlinearly as tasks lengthen, 27-paper synthesis finds
27-paper synthesis finds LLM agent failures compound nonlinearly with task length. Six failure clusters identified across 19 benchmarks.
How to Use MCP Servers for Financial Data
MCP servers turn financial data sources into auditable, replaceable protocol endpoints. For Claude Code users building agentic BFSI systems, this means 90% fewer custom integrations and regulator-ready logging.
MirrorCode Benchmark Costs $2,600 Per Run, Challenges AI Coding Limits
Epoch AI and METR launched MirrorCode, a $2,600-per-run coding benchmark. Claude Opus 4.7 leads with 56% solve rate.
RIFT-Bench Tests 45 Agentic Systems With Dynamic Red-Teaming
RIFT-Bench evaluates 45 agentic AI systems via a graph-driven two-phase pipeline, enabling unified security comparison across heterogeneous architectures.
WorldBench: Top MLLM Scores 64% on Visually Diverse Benchmark
WorldBench, a new multimodal benchmark, tests 15 MLLMs on visually diverse images. Top model scores 64.0%, exposing fundamental gaps in visual understanding.
DeepMind paper: hidden web content hijacks agents 86% of the time
DeepMind catalogues 6 attack types where hidden web content hijacks AI agents up to 86% of the time, reframing safety from model alignment to environment trust.
Meta-Stanford Survey: Code as Agent Harness Improves AI Reasoning
Meta, Stanford, Illinois survey argues AI agents work better with code as their main working layer, calling it an agent harness.
ARMOR 2025: Military Safety Benchmark Exposes LLM Gaps Across 21 Models
ARMOR 2025 benchmark tests 21 LLMs against military legal doctrines, revealing critical safety gaps that civilian benchmarks miss.
New CASIA Benchmark Exposes Fragmented Face Swapping Evaluation
CASIA researchers released a face swapping survey and benchmark on April 27, 2026, aiming to standardize evaluation across fragmented GAN and diffusion model methods.
Recursive Multi-Agent Systems Top Hugging Papers; Eywa Bridges LLMs and Scientific Models
Recursive Multi-Agent Systems leads Hugging Papers with 242 upvotes. Eywa and OneManCompany signal a move from chat-based to structural agent collaboration.
How a Custom Multimodal Transformer Beat a Fine-Tuned LLM for Attribute
LeBonCoin's ML team built a custom late-fusion transformer that uses pre-computed visual embeddings and character n-gram text vectors to predict ad attributes. It outperformed a fine-tuned VLM while running on CPU with sub-200ms latency, offering calibrated probabilities and 15-minute retraining cycles.
SSL: Structured Skill Language Boosts Skill Discovery MRR to 0.707
Researchers propose SSL, a three-layer typed JSON representation for AI agent skills, replacing unstructured SKILL.md prose. Using an LLM normalizer, SSL improves Skill Discovery MRR from 0.573 to 0.707 and Risk Assessment macro F1 from 0.744 to 0.787 on a newly released 6,184-skill corpus.
AI Memory Survey: Three Systems Needed for Human-Like Recall
A new survey paper proposes that modern AI requires three distinct memory systems—parametric, retrieval, and agent memory—to achieve human-like cognition, highlighting control as the key bottleneck.
40-Author Survey Unveils 'Levels × Laws' Framework for Agent World Models
A 40-author survey introduces a 'levels × laws' framework for world models in AI agents, spanning 3 capability levels and 4 law regimes, synthesizing 400+ works. It provides a shared vocabulary for designing and evaluating world models across traditionally siloed research communities.
Agent Harnessing: The Infrastructure That Makes AI Agents Work
A detailed technical guide argues that the model is not the hard part of building AI agents. The six-component harness — context management, memory, tools, control flow, verification, and coordination — is what separates production-grade agents from those that fail silently.
CAST: A New Framework for Semantic-Level Complementary Recommendations
Researchers propose CAST, a sequential recommendation framework that models transitions between discrete item semantic codes (e.g., specifications) and injects LLM-verified complementary knowledge. It achieves significant performance gains by moving beyond simplistic co-purchase statistics to capture genuine complementarity.
ECLASS-Augmented Semantic Product Search
Researchers systematically evaluated LLM-assisted dense retrieval for semantic product search on industrial electronic components. Augmenting embeddings with ECLASS hierarchical metadata created a crucial semantic bridge, achieving 94.3% Hit_Rate@5 versus 31.4% for BM25.
UniRec: A New Generative Recommendation Model Bridges the 'Expressive Gap'
A new paper introduces UniRec, a generative recommendation model that closes the performance gap with traditional discriminative models by prefixing item sequences with structured attributes like category and brand. It achieved a +22.6% improvement in offline metrics and significant online gains in CTR and GMV when deployed on Shopee.
Google DeepMind Maps AI Attack Surface, Warns of 'Critical' Vulnerabilities
Google DeepMind researchers published a paper mapping the fundamental attack surface of AI agents, identifying critical vulnerabilities that could lead to persistent compromise and data exfiltration. The work provides a framework for red-teaming and securing autonomous AI systems before widespread deployment.
Ethan Mollick Proposes AI Model 'Changelog' for Task-Level Performance Tracking
AI researcher Ethan Mollick argues labs should release a 'changelog' alongside model cards, detailing performance changes on individual tasks. This would increase transparency as model updates become more frequent.
FeCoSR: A Federated Framework for Cross-Market Sequential Recommendation
A new arXiv paper introduces FeCoSR, a federated collaboration framework for cross-market sequential recommendation. It tackles data isolation and market heterogeneity by enabling many-to-many collaborative training with a novel loss function, showing advantages over traditional transfer approaches.
HORIZON Benchmark Diagnoses Long-Horizon Failures in GPT-5 and Claude Agents
A new benchmark called HORIZON systematically analyzes where and why LLM agents like GPT-5 and Claude fail on long-horizon tasks. The study collected over 3100 agent trajectories and provides a scalable method for failure attribution, offering practical guidance for building more reliable agents.
Fine-Tuning vs RAG: Clarifying the Core Distinction in LLM Application Design
The source article aims to dispel confusion by explaining that fine-tuning modifies a model's knowledge and behavior, while RAG provides it with external, up-to-date information. Choosing the right approach is foundational for any production LLM application.
SID-Coord: A New Framework for Balancing Memorization and Generalization
A new arXiv paper introduces SID-Coord, a framework that integrates trainable Semantic IDs (SIDs) with traditional Hashed IDs (HIDs) in ranking models. It aims to solve the memorization-generalization trade-off, improving performance on long-tail items. Online A/B tests in a production short-video search system showed statistically significant improvements in engagement metrics.