Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
2 results for “reasoning LLM”
Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings
A new arXiv preprint evaluates frontier LLMs as batch optimizers, finding they underperform classical methods on numerical test functions but outperform them in semantically rich, discrete optimization tasks — suggesting their strength lies in reasoning over language-structured spaces rather than numeric search.
Sep 4, 2026
Kara: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression
Kara is a new sliding-window KV cache compression method for reasoning LLMs that improves decoding throughput and reduces memory overhead by selectively preserving flexible-sized semantic chunks of the key-value cache during inference.
Published Jul 3, 2026 · Analyzed Jul 6, 2026