Research and signals we are watching.

Accelerating GPT-5.6 Sol Ultrafast

AI At Home Part 1: A Box Of Scraps

Show HN: MCP Memory – Fast Agent Memory Using Google's OKF and SQLite FTS5

Choosing an AI model: one prompt, 11 models, different results

The Download: kids’ thoughts on AI, and female clones of male mice

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. How kids feel about AI, in their own words —Jen Swetzoff and…

How kids feel about AI, in their own words

When we set out to talk to kids about artificial intelligence, we thought we knew what we’d hear. We expected some to tell us they were using it to cheat a little, the way Millennials and Gen Xers…

Launch HN: Bullet (YC S26) – A Faster Coding Agent

Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes

arXiv:2608.11207v1 Announce Type: new Abstract: When two LLM agents with structurally opposed objectives interact across multiple turns, the absence of a shared goal function produces not competition…

Distribird: Literature-Informed Prior Distribution Design for Bayesian Model Calibration

arXiv:2608.11210v1 Announce Type: new Abstract: Bayesian calibration of process-based models requires a prior distribution for each model parameter. Despite decades of methodological work,…

A Forced-Structure Reduction and Verifiable Bounds for Conway's 99-Graph

arXiv:2608.11211v1 Announce Type: new Abstract: Conway's 99-graph problem asks whether a strongly regular graph with parameters $\mathrm{srg}(99,14,1,2)$ exists. We report a systematic, fully…

Detecting a Route Flip Is Easier Than Knowing Whether to Fix It: Causal Route-Mediated Damage in Quantized Mixture-of-Experts

arXiv:2608.11212v1 Announce Type: new Abstract: Top-k Mixture-of-Experts (MoE) routing is discontinuous, so a deployment-motivated numerical disturbance -- simulated 4-bit KV-cache quantization read…

Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop

arXiv:2608.11215v1 Announce Type: new Abstract: Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase…

AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research

arXiv:2608.11216v1 Announce Type: new Abstract: World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe…

MaSRead: Content-Addressed Reading of Replicated Latent Stores

arXiv:2608.11218v1 Announce Type: new Abstract: Independent agents that reason in latent space can share computed state as key-value cache fragments rather than text. Merged by a conflict-free…

From Monolithic to Modular: Segment-level Automatic Prompt Optimization

arXiv:2608.11219v1 Announce Type: new Abstract: Automatic Prompt Optimization (APO) often rewrites prompts monolithically, which can improve one behavior while degrading others. We present SAPO, a…

LLMs in Process Diagram Engineering: From Optimal PFDs to Validated P&IDs

arXiv:2608.11220v1 Announce Type: new Abstract: Nowadays, the creation of a process flow diagram (PFD) and its subsequent transformation into a piping and instrumentation diagram (P&ID) is…

A Conceptual Framework for Refining Influence Knowledge from Simulation Evidence in Cyber-Physical Systems

arXiv:2608.11221v1 Announce Type: new Abstract: Cyber-physical systems (CPS) are typically developed by multiple stakeholders who produce artefacts tailored to their specific domains of expertise.…

Harnessing agent memory to build lifelong AI partners for materials scientists

arXiv:2608.11224v1 Announce Type: new Abstract: Materials research advances through accumulated experience - scripts that work, protocols that are trusted, warnings attached to failed calculations or…

Identity from the Outside: A Conceptual Framework and Research Program for AI Personality Clones

arXiv:2608.11225v1 Announce Type: new Abstract: AI "personality clones" force a re-examination of personal identity in operational terms. Setting aside the hard problem of consciousness, we approach…

Cutting AI Datacenter Energy with Reinforcement Learning: Measured Power Control of LLM Training from One GPU to the Fleet

arXiv:2608.11226v1 Announce Type: new Abstract: Reinforcement-learning post-training dominates modern language-model development, yet its power behavior on GPU hardware has not been characterized,…