Agent Languages, Sampling Ceilings, and Abstention
Three new papers on agents inventing symbolic languages to cut reasoning tokens by 3-6x, sampling ceilings that waste inference compute, and context-engineering to double agentic abstention rates.
Articles Tagged "Multi-Agent"
Tandem Training, World Models, and Efficient Agents
Three new arXiv papers on making RL reasoning legible across models, fixing broken world model latent states, and training small agents to beat their teachers.
DeepMind Maps Four Routes from AGI to Superintelligence
A 57-page DeepMind paper by co-founder Shane Legg identifies four pathways from AGI to superintelligence and six bottlenecks that could block each route.
Sakana Fugu
Sakana AI's orchestrator model that dynamically coordinates Claude Opus 4.8, GPT-5.5, and Gemini 3.1 Pro to beat each of them individually on SWE-Bench Pro, GPQA-Diamond, and eight other benchmarks.
AI Research: Orchestration Beats Scale, Small Models Win
Sakana Fugu tops SWE-Bench Pro by routing tasks across rival LLMs, Microsoft's 9B browser agent beats OpenAI Operator, and a 3B model from Weibo matches DeepSeek V3.2 on math.
Emergent Alignment, Agent Memory, and Smarter Reasoning
Three arXiv papers: a conscience mechanism for ethical training, shared memory for agent populations, and selective verification that cuts test-time compute waste.
AI Engrams, Cognitive Debt, and Agent Trust
Three new papers tackle what lives inside a trained model, how AI dependence erodes human cognition, and whether AI teams can calibrate trust.
Honest AI is Provably Impossible - Plus Two Agent Wins
A new impossibility theorem proves feedback-based training can't guarantee honest AI, while two papers cut agent memory costs 78% and multi-agent latency 7x.
Claude Opus 4.8 Review: Reliability Over Raw Scores
Claude Opus 4.8 sets new highs on SWE-bench Pro and long-context tasks while a 4x improvement in code flaw detection may matter more than any benchmark number.
Kore.ai Artemis Review: Enterprise Agent Control Plane
Kore.ai's Artemis platform brings a compiled blueprint language and governance-first architecture to enterprise multiagent AI - ambitious, but Azure-only for now.
Claude Opus 4.8
Anthropic's May 2026 flagship model delivers 69.2% on SWE-bench Pro, dynamic parallel workflows in research preview, and Effort Control - all at $5/$25 pricing.
Anthropic Ships Opus 4.8 with Multi-Agent Workflows
Claude Opus 4.8 launches with dynamic workflows for parallel subagent orchestration, hitting 69.2% on SWE-bench Pro and introducing granular effort controls at unchanged pricing.
