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.
Science
Faster Agents, Skewed Evals, and Brand Bias in LLMs
Three new papers: agents that compile runs into 8-13x faster state machines, benchmark scores that shift with compute budget, and big brands monopolizing LLM recommendations.
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.
Agents Hit 89%, Evals Get a Schema, Memory Falls Short
Three papers from today's arXiv: workplace agents jumped from 43% to 89% task completion in two years, a 47-researcher coalition ships a unified eval schema, and agent memory only helps when similarity tops 0.8.
Tool Blindness, Tree Search, and the Road to ASI
Three new papers expose a 50-point gap in agent tool knowledge, show tree search tripling inference throughput, and map the research between AGI and superintelligence.
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.
Context Overload, Memory Leaks, and Agent Safety
Three new arXiv papers expose how context bloat tanks agent performance, agent memory bleeds private data, and misaligned behavior spreads through multi-agent systems.
MCP Exploit Risk, Sycophancy Scores, and Agent Self-Harm
New research reveals MCP error messages triple agent attack success rates, ranks eight models on sycophancy with Claude scoring best, and finds self-evolving agents make 30-42% false edits.
Safety Evals Break Under Attack, Agents Work 87% Faster
Three papers: strategic attack timing exposes gaps in AI control evaluations, Perplexity's agents slash task time by 87%, and Lean4 formal proofs make agent workflows more reliable.
AI Sabotage Blind Spots, Code Drift, and ZK Proofs
Three new arXiv papers expose how developers miss AI sabotage 94% of the time, why LLMs converge structurally in code evolution, and how ZK proofs could verify frontier AI training.
AI Attachment, Smarter Spending, and Cascading RAG Errors
Three new papers tackle how routine AI use quietly rewires emotional habits, how to spend compute where failures cost most, and why agentic RAG errors compound before anyone notices.
When to Stop - Overthinking, Handoffs, and Abstention
Three new papers show that AI agents fail not by doing the wrong thing, but by doing things when they should have stopped.
