🛰️ Daily AI Frontier
‹ back to 2026-08-02

Zero-Mem: Zero-Token Memory Operations for LLM Agents

Research LLM Agents

Ranking

Overall 76
Content 80
Popularity 67

Observed public metrics from 1 member.

Merged summary

TL;DR - Zero-Mem is an agent memory system that removes LLM calls from all memory operations, keeping raw interaction traces as the record and invoking a model only for final question answering. It matters because it cuts the recurring token and latency overhead that generation-based memory pipelines impose while avoiding lossy intermediate summaries.

  • Memory is organized in two complementary views: an entity–context graph for cross-interaction connections, and a temporal hierarchy that preserves conversational locality and session state; per query, the two views are weighted and retrieved from jointly.
  • "Zero-token" means no step outside final QA consumes LLM input or output tokens; encoder computation is accounted for separately.
  • Deterministic calibration discards conflicting evidence and grounds the reader's answer in retrieved original traces rather than generated records.
  • On long-memory and long-context QA benchmarks, it reports competitive accuracy with a 57.6% reduction in memory-operation time versus the fastest compared baseline (same reader and context budget); ablations support both views and their query-dependent coordination.

Sources (1)

Zero-Mem: Zero-Token Memory Operations for LLM Agents

arXiv cs.CL Yilin Xiao, Zhehan Zhu, Yujing Zhang, Jin Chen, Zijin Hong, Luyao Zhuang, Qinggang Zhang, Shengyuan Chen, Xiaocao Ouyang, Lingfei Ren, Xiao Huang 2026-07-31 arXiv:2607.29377
Public signals Hugging Face upvotes 12
Providers: Hugging Face · Upvotes 12 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-08-31 14:29:40.921180 UTC

TL;DR - Zero-Mem is an agent memory system that removes LLM calls from all memory operations, keeping raw interaction traces as the record and invoking a model only for final question answering. It matters because it cuts the recurring token and latency overhead that generation-based memory pipelines impose while avoiding lossy intermediate summaries.

  • Memory is organized in two complementary views: an entity–context graph for cross-interaction connections, and a temporal hierarchy that preserves conversational locality and session state; per query, the two views are weighted and retrieved from jointly.
  • "Zero-token" means no step outside final QA consumes LLM input or output tokens; encoder computation is accounted for separately.
  • Deterministic calibration discards conflicting evidence and grounds the reader's answer in retrieved original traces rather than generated records.
  • On long-memory and long-context QA benchmarks, it reports competitive accuracy with a 57.6% reduction in memory-operation time versus the fastest compared baseline (same reader and context budget); ablations support both views and their query-dependent coordination.
item →