// Language Models Need Sleep // Let your agents "sleep", folks. On a serious note, this is a fascinating paper on getting the most from long-horizon agents. Here is the problem with agents today: Attention scales badly with context length, so long-horizon agents keep paying a
@dair_ai
-
LLM Context Cost Optimization and Efficiency Strategy
By
–
// The Efficiency Frontier in LLMs // (bookmark this one) How much are you overpaying for context you do not need? It turns out that context costs dominate production LLM bills, and the right strategy depends on how often you reuse preprocessing. Modeling that explicitly lets
-
Microsoft Paper on Self-Evolving Agent Skills
By
–
New paper from Microsoft on Self-Evolving Agent Skills
-
Top AI Papers of the Week: Agents and Architecture
By
–
The Top AI Papers of the Week (May 18 – 24): – AIRA
– MetaCogAgent
– Memory as a Model
– Code as Agent Harness
– Weak-Model Critic-Comparator
– OpenAI Disproves the Unit Distance Conjecture
– Production Agent Architecture Methodology Read on for more: -
Frontier Models and Scientific Progress Forecasting Study
By
–
Can frontier models forecast scientific progress? Mostly no, but here is why. This work looks at 4,760 scientific events across disciplines. Frontier models can identify plausible research directions when given options. They cannot reliably predict whether an advance will land,
-
Paper: Memory-as-a-Model for LLMs Enables Continual Learning
By
–
// Memory as a Model // The paper augments any LLM with a separate trained memory model that stores, retrieves, and integrates facts on its behalf. It decouples memory updates from base-model weight updates. It achieves continual-learning robustness without catastrophic
-
MetaCogAgent: metacognitive multi-agent task delegation paper
By
–
NEW paper worth reading: MetaCogAgent MetaCogAgent equips a multi-agent system with metacognition so each agent decides whether it should answer or delegate. In other words, it aims for self-aware task delegation rather than fixed routing. The bottleneck in multi-agent systems
-
Meta paper: Agentic Discovery of Neural Architectures
By
–
NEW paper from Meta: Agentic Discovery of Neural Architectures. This is a hot new area of research! Keep an eye on it.
-
Paper: GPT-5.4 Nano with Critic-Comparator Reaches SWE-bench Parity
By
–
NEW paper worth reading. GPT-5.4 nano plus a critic-comparator orchestration loop hits 76.4% on SWE-bench Verified, matching standalone Gemini 3 Pro and Claude Opus 4.5 Thinking. The trick is to select from k=8 weak-model proposals using execution and proof signals. What does
