view article Article Palette: teaching a small model to build decks in your design language ibm-research • 12 days ago • 21
view article Article Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA? ibm-research • 12 days ago • 37
view article Article Same Model, Different Harness: CUGA, Hermes, and Deep Agents — When to Pick CUGA? ibm-research • 12 days ago • 37
view article Article ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model ibm-research • 26 days ago • 28
view article Article Build real agentic apps using CUGA: two dozen working examples on a lightweight harness ibm-research • Jun 23 • 40
A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks Paper • 2605.28556 • Published May 27 • 74
view article Article Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic ibm-research • Jun 1 • 92
view article Article Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents ibm-research • Apr 15 • 30