Adding procedural skills to an LLM agent is typically evaluated by average improvement in task success. However, this metric hides an important cost: skills can also make agents worse. We measure both sides by comparing agents with and without skills across…
PRISM indexes and ranks — it never republishes. The full piece lives with its author on arxiv.org.
Read on arxiv.org↳
Stories the engine considers adjacent to this one.
Intelligence arXiv
Geometry Foundation Models (GFMs) have substantially advanced monocular 3D reconstruction, yet extending this capability to 4D dynamic understanding remains a fundamental challenge. Most existing motion perception methods (e.g., sparse tracking, dense…
Intelligence arXiv
A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input data. For matrix-valued inputs, relevant matrix-level relationships can be characterised through spectral…
Intelligence arXiv
Commercial large language models are increasingly used as knowledge references, yet their stance on contested scientific claims is neither stable nor transparent. We tested how four major LLM families (Claude, Grok, GPT, Gemini) evaluate ethnonationalist…
Intelligence arXiv
Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approach is to close the research loop with a large language model (LLM) reviewer. However, such reviewers remain…
