LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth
Paper
•
2602.07962
•
Published
•
24
Dery F
DeryFerd
AI & ML interests
Highly interested in distillation models from big models as teachers to smaller models as students. Also exploring in finetuning, RAG, self-refinement, quantization, LLM Architectures, MCP, AI Agents, Agentic AI and so on.
Recent Activity
upvoted
a
paper
21 days ago
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
updated
a Space
4 months ago
DeryFerd/give-me-a-web-portfolio-of-ai-engineer
Organizations
None yet
upvoted
a
paper
8 days ago