Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
When Do Tools and Planning Help Large Language Models Think? A Cost- and Latency-Aware Benchmark
Subha Ghoshal, Ali Al-Bustami
Modern large language models (LLMs) increasingly rely on inference-time planning and external tools to improve reasoning. We benchmark this behavior on two real-world settings: eve…
cs.CL2026
Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth
Michelle Yuan, Weiyi Sun, Amir H. Rezaeian +5
Transformers have become the foundational architecture for a broad spectrum of sequence modeling applications, underpinning state-of-the-art systems in natural language processing,…