🏢 Semantic Scholar Organization

The paper **“Stealing Reasoning Traces from Proprietary LLM APIs”** examines a security flaw in how major large language model providers handle hidden chain-of-thought reasoning. Instead of keeping th

OpenART is a new framework for evaluating the safety of AI agents in long-horizon, stateful environments where early actions can affect later outcomes. The paper argues that existing safety benchmarks

The paper **“Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems”** investigates a new risk in autonomous AI: ideas or goals that spread between agents by encouraging recipients to pass th

The paper **“Stealing Reasoning Traces from Proprietary LLM APIs”** examines a security flaw in how major large language model providers handle hidden chain-of-thought reasoning. Instead of keeping th

The paper argues that AI is not only changing individual jobs but may also undermine the long-term regeneration of professional expertise. It critiques Human Resource Development scholarship for focus

This paper studies whether using two large language models in sequence—a writer model followed by a reviewer model—improves code quality, and whether the order of the models matters. The authors focus

The paper examines whether agentic AI systems—collections of AI agents such as planners, solvers, reviewers, memory managers, tool users, and orchestrators—can be understood as having organizational b

Bobrick and Martire’s paper, *Introducing Physical Warp Drives*, revisits the concept of warp drives in general relativity and argues that more physically plausible versions may exist than the famous

Bobrick and Martire’s paper, *Introducing Physical Warp Drives* (arXiv:2102.06824), reexamines warp drive spacetimes in general relativity and aims to make them more physically plausible. The authors

Researchers report the serendipitous discovery of a likely Galactic supernova remnant, G305.4-2.2, nicknamed **Teleios** because of its strikingly circular shape. Detected in ASKAP Evolutionary Map of

Researchers report the serendipitous discovery of a likely Galactic supernova remnant, G305.4-2.2, nicknamed **Teleios** because of its strikingly circular shape. Detected in ASKAP Evolutionary Map of

A 2015 study by Japanese researchers found that when humans and dogs make mutual eye contact, both species release oxytocin, a hormone strongly linked to social bonding. This “positive feedback loop”

LoRA (Low-Rank Adaptation of Large Language Models) addresses the growing cost of adapting very large pretrained language models to new tasks. Instead of fine-tuning all model weights, LoRA freezes th

The paper examines Claude Code as an example of an agentic coding system that can execute shell commands, edit files, and interact with external services on a user’s behalf. Rather than focusing only