2 papers
cs.AI2026
The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents
Darshan Tank, Baran Nama
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 wo…
cs.AI2026
ROMA: Recursive Open Meta-Agent Framework for Long-Horizon Multi-Agent Systems
Salaheddin Alzu'bi, Baran Nama, Arda Kaz +6
Current agentic frameworks underperform on long-horizon tasks. As reasoning depth increases, sequential orchestration becomes brittle, context windows impose hard limits that degra…