How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
Paper • 2604.04323 • Published • 29
David K. Johansson
dkjo8
·
AI & ML interests
Energy based reasoning, gradient based optimization, world models
Recent Activity
reacted to BibbyResearch's post with 🔥 1 day ago
Bibby AI is now #3 rank and live on ProductHunt.
It's time to support the AI co-author for research you wish existed.
Producthunt - https://www.producthunt.com/products/bibby-ai
Please upvote, comment, give critical feedback.
The research community has shown immense trust. published a Space 1 day ago
PolishedSnow/READMEOrganizations
upvoted 9
papers 1 day ago
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
Paper • 2604.05404 • Published • 36
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
Paper • 2604.03922 • Published • 49
GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers
Paper • 2604.02648 • Published • 39
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
Paper • 2604.01591 • Published • 33
Learning to Retrieve from Agent Trajectories
Paper • 2604.04949 • Published • 61
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Paper • 2604.06132 • Published • 102
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Paper • 2604.05015 • Published • 217
Reasoning as Energy Minimization over Structured Latent Trajectories
Paper • 2603.28248 • Published • 1