cd /news/artificial-intelligence/commitkv-lifecycle-aware-kv-cache-co… · home topics artificial-intelligence article
[ARTICLE · art-91410] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents

Researchers introduced CommitKV, a KV cache compression method that identifies key-value lifecycles through commit transitions, reducing memory use and accelerating inference for multi-turn ReAct agents. In experiments, CommitKV achieved higher accuracy than existing KV cache compression methods while lowering memory and speeding up end-to-end inference.

read1 min views1 publishedAug 11, 2026

arXiv:2608.07855v1 Announce Type: new Abstract: Multi-turn Reasoning-and-Acting (ReAct) agents accumulate growing trajectories of reasoning, tool calls, and observations. Their key-value (KV) caches grow accordingly, increasing memory use and attention cost during model inference. Existing KV cache compression methods reduce these costs by evicting states with low attention scores. However, low attention in the current turn does not imply future irrelevance, as temporarily inactive information may become important later. Snapshot-based eviction methods therefore do not explicitly distinguish temporarily dormant information from information that appears to have completed its role. In this paper, we present CommitKV, which identifies KV lifecycles through commit transitions. Specifically, CommitKV first divides completed agent events into token pages and compares each eligible page's deletion effect before a tool-call commit and after the commit's returned observation has been incorporated. Based on these paired measurements, CommitKV distinguishes dormant pages from high-to-low completion candidates. It then applies a greedy joint test, accepting candidates for retirement only when their combined post-commit effect remains bounded. Finally, at a later compression checkpoint, accepted pages are excluded, a bounded set of pages awaiting post-commit measurement is protected, and the remaining KV states are retained within the cache budget using the same token indices for keys, values, and absolute positions. These mechanisms ensure that CommitKV can distinguish dormant information from information that has completed its observed role and can be safely removed. Experiments on various benchmarks show that CommitKV reduces agent memory use, accelerates end-to-end inference, and achieves higher accuracy than existing KV cache compression methods.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @commitkv 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/commitkv-lifecycle-a…] indexed:0 read:1min 2026-08-11 ·