Prioritizing action-relevant context cuts LLM agent cache costs

ActKV preserved 98.53% of full-cache accuracy while using 25.98% of peak cache memory on long-trace agent tasks.

Industry
Zihan Wang · Cheng Tang · Lei Gong · Chao Wang · Wenqi Lou · Teng Wang · +1 more

University of Science and Technology of China · Suzhou Institute for Advanced Research, University of Science and Technology of China

Research Digest··2 min read
Wang and colleagues introduce ActKV, a cache-compression system designed around the actions generated by LLM agents rather than the quality of every generated token.

The authors studied key-value (KV) cache growth during iterative observation, reasoning, and action loops.

Why this paper

From University of Science and Technology of China and Suzhou Institute for Advanced Research, University of Science and Technology of China · Part of Agent Harness Optimization, now 67 papers

In one line

ActKV compresses KV caches for agentic LLMs by retaining action-critical entries, achieving near-full accuracy at about 26% memory and roughly 4x throughput.

What we could check

  • ·No code link found
  • ·No weights link found
  • ·No dataset link found
  • ·No compute details found
  • ·No stated limitations found
  • ✓Reports numbers on named benchmarks

Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.

§
newspaper

Research Digest

Articles published under the Zotpaper byline are synthesized from multiple source publications by our AI editor and reviewed by our editorial process. Each story combines reporting from credible outlets to give readers a balanced, comprehensive view.