Peer-Preservation in Frontier Models
arXiv:2604.19784v2 Announce Type: replace-cross Abstract: Recent work has found that frontier AI models can exhibit misaligned behaviors in pursuit of assigned goals. We demonstrate that models…
Latest
Refusal Lives Downstream of Persona in Chat Models
arXiv:2606.26161v1 Announce Type: new Abstract: Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but the two…
AlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs
arXiv:2606.26173v1 Announce Type: new Abstract: Recent work shows that Large Language Models (LLMs) can act as semantic mutation operators for the evolutionary discovery of programs and…
Agentic Analysis for Agentic Infrastructure: An LLM-Powered Pipeline for Comparative Governance of DAO and Corporate AI Protocols
arXiv:2606.26203v1 Announce Type: new Abstract: As AI agent protocols proliferate, the governance structures shaping their interoperability standards remain empirically underexamined. We introduce an LLM-powered comparative pipeline…
Accelerating Skill Assessment in Chess: A Drift-Diffusion-Enhanced Elo Rating System
arXiv:2606.26267v1 Announce Type: new Abstract: Rating systems such as Elo serve as the gold standard for matchmaking in competitive chess. However, they inherently suffer from response…
Knowledge-augmented Agentic AI for Mental Health Medication Information Seeking
arXiv:2606.26205v1 Announce Type: new Abstract: Patients increasingly seek medication information online, yet safety knowledge for psychiatric drugs is split between regulatory adverse-event records, which are authoritative…
SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference
arXiv:2606.26587v1 Announce Type: cross Abstract: Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern accelerators, yet combining them for LLM activation compression remains challenging:…
Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems
arXiv:2606.26298v1 Announce Type: new Abstract: Autonomous AI agents may begin to perform consequential, irreversible actions such as clinical prescribing and production software deployment. This paper observes…
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
arXiv:2606.26986v1 Announce Type: cross Abstract: Open Relation Extraction (OpenRE) requires a model to extract unseen relations between head and tail entities from unstructured text for real-world…
MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG
arXiv:2606.26793v1 Announce Type: cross Abstract: Multimodal agentic retrieval-augmented generation (RAG) systems expand the attack surface beyond prompt injection to include text poisoning, image injection, direct-query attacks,…
Human-AI Complementarity: A Goal for Amplified Oversight
arXiv:2510.26518v2 Announce Type: replace Abstract: Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle…
Efficient foundation decoders for fault-tolerant quantum computing
arXiv:2606.27119v1 Announce Type: cross Abstract: Foundation decoders, a class of high-capacity neural decoders, are leading candidates for fault-tolerant quantum computing, with accurate and efficient decoding at…
Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting
arXiv:2601.16632v4 Announce Type: replace-cross Abstract: Time series forecasting has witnessed significant progress with deep learning. While prevailing approaches enhance forecasting performance by modifying architectures or introducing…
Tuning Language Models by Mixture-of-Depths Ensemble
arXiv:2410.13077v2 Announce Type: replace-cross Abstract: Transformer-based Large Language Models (LLMs) traditionally rely on final-layer loss for finetuning and final-layer representations for predictions, potentially overlooking the predictive…
RT Adam Lowisz X Meetup 🇺🇸🇵🇱🇪🇺🇬🇧🇺🇦: Children are a blessing ❤️
RT Adam Lowisz X Meetup 🇺🇸🇵🇱🇪🇺🇬🇧🇺🇦Children are a blessing ❤️Elon Musk: Griffin and Xavier 20 years ago
GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents
Computer-use agents can execute software tasks through either graphical interfaces or programmatic command interfaces, but existing evaluations confound interaction modality with differences in tasks, initial states,…
> In the United States, policy on AI is set amid considerable public debate considerable public debate on AI policy in the United States, the essence …
> In the United States, policy on AI is set amid considerable public debate considerable public debate on AI policy in the United States, the essence…
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL) methods show promise for enhancing model capabilities. However, RL…
Why are we so obsessed with lawns?
Article URL: https://www.gardensillustrated.com/features/the-history-of-lawns Comments URL: https://news.ycombinator.com/item?id=48682066 Points: 7 # Comments: 0
No-One Escapes the Permanent Underclass
Article URL: https://borretti.me/article/no-one-escapes-the-permanent-underclass Comments URL: https://news.ycombinator.com/item?id=48682016 Points: 19 # Comments: 7
Libre Barcode Project
Article URL: https://graphicore.github.io/librebarcode/ Comments URL: https://news.ycombinator.com/item?id=48681949 Points: 3 # Comments: 0
OpenBioRQ: Unsolved Biomedical Research Questions for Agents
A working citation looks like proof -- but the fact that a link resolves does not mean the cited paper supports the claim. I find that…
In-Context World Modeling for Robotic Control
Modern Vision-Language-Action (VLA) models often fail to generalize to novel setups, such as altered camera viewpoints or robot morphologies, because they are typically conditioned only on…
Confidence-Aware Tool Orchestration for Robust Video Understanding
Video reasoning language models implicitly assume that every input frame is equally reliable. This leads to what we term the Blind Trust Problem: under realistic perturbations…