agent/papers/items/2026-2607-10582-memdecay-region-aware-kv-cache-eviction-for-efficient-llm-agent-inference.md

Paper: MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference

---

type: paper title: "MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference" authors: Venkatesha Matam, Keon Kim year: 2026 venue: arXiv url: https://arxiv.org/abs/2607.10582 code_url: source: arxiv collected_at: 2026-07-27 published_at: 2026-07-12 updated_at: 2026-07-12 status: queued relevance: high topics:

• agent-evaluation
• coding-agent
• memory
• planning
• reasoning
• tool-use methods:

benchmarks:

models:

datasets:

• cs.LG related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 17 collection_queries: planning-agent

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: planning-agent
• inferred topics: agent-evaluation, coding-agent, memory, planning, reasoning, tool-use
• arXiv categories: cs.LG
• collection score: 17

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2607.10582