2 papers
cs.CL2026
Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents
Jianghong Zhou, Hao Rong, Chen Lin +1
Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted memory saves reasoning steps and…
cs.AI2026
CAX-Agent: A Lightweight Agent Harness for Reliable APDL Automation
Chenying Lin, Yichen Hai, Yi He +3
Large language models deployed for MAPDL finite-element simulation face practical reliability challenges: without structured execution control, tool encapsulation, and fault recove…