arXiv:2608.11227v1 Announce Type: new Abstract: Activation steering modifies a language model by adding a learned direction to its hidden activations,…
Synchronizing Beliefs with Second-Order Theory-of-Mind in Human-Autonomy Teams (Extended Version)
arXiv:2608.11229v1 Announce Type: new Abstract: Comparative feedback, asking people which of two behaviors they prefer, has become a standard way to align…
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…
The Video Production Stack Now Fits on One Desk: LTX-2.5 Launches as NVIDIA-Accelerated Open Weights World Model
LTX-2.5 brings frontier video generation to local NVIDIA hardware: 6.8-second clips, native multishot, day-one ComfyUI, open weights.
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…
AI News Brief Hourly Summary 2026-08-13 07h : 11 posts
11 posts were published in the last hour 4:32 : From Monolithic to Modular: Segment-level Automatic Prompt Optimization 4:32 : A Conceptual Framework for Refining Influence Knowledge from Simulation Evidence in Cyber-Physical Systems 4:32 : LLMs in Process Diagram Engineering:…
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…
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…
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…
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…
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…
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 $\mathrm{srg}(99,14,1,2)$…
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…
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…
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…
OpenAI launches ChatGPT desktop app for Linux
OpenAI is finally bringing a dedicated ChatGPT desktop app to Linux operating systems.
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.…
AI News Brief Hourly Summary 2026-08-13 06h : 12 posts
12 posts were published in the last hour 3:32 : TrAC: Trace-Conditioned Answer Consistency for Efficient Uncertainty Quantification in LLMs 3:32 : Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog 3:32 : AttriMem: Attribution-Guided Process Feedback…