AuthorsB.Y. Yan, Chaofan Li, Hongjin Qian et al.
TL;DR
General Agentic Memory (GAM) uses a dual Memorizer–Researcher deep-research mechanism to JIT-build context, reaching 97.70% accuracy on RULER retrieval vs 94.25% for RAG (+3.45 points).
Read our summary here, or open the publisher PDF on the next tab.
THE PROBLEM
Static ahead-of-time memory compresses trajectories into lightweight summaries, so memorization is inevitably subject to severe information loss and missing fine-grained details.
When LLM agents rely only on compressed memory, they cannot satisfy nuanced information needs, causing degraded task completion on long-context benchmarks like LoCoMo and HotpotQA.
HOW IT WORKS
General Agentic Memory (GAM) uses a dual design with a Memorizer, Researcher, memory, page-store, and explicit pages to manage long trajectories.
You can think of GAM like RAM and disk: memory is a compact index, while the page-store is a full archive that the Researcher actively searches.
This just in time deep research mechanism lets GAM plan, search, and reflect over complete history, enabling optimized contexts that a plain context window cannot construct.
DIAGRAM
This sequence diagram shows how General Agentic Memory (GAM) runs the Researcher planning, searching, and reflection loop over the page-store for a client request.
DIAGRAM
This flowchart shows how General Agentic Memory (GAM) is evaluated across datasets, baselines, and ablation settings.
PROCESS
Memorizer.memorize
GAM uses Memorizer.memorize to turn each new session and existing memory into a concise memo, incrementally updating the global memory state.
Memorizer.page
GAM runs Memorizer.page to generate a header from memory, decorate the session into a page, and append it into the page-store.
Researcher.plan
Given a request, GAM calls Researcher.plan with memory and tools to analyze information needs and produce concrete search actions.
Researcher.reflect
After searching and integration, GAM invokes Researcher.reflect to decide if information is sufficient or to trigger another deep research round.
KEY CONTRIBUTIONS
General Agentic Memory framework
GAM introduces a dual-agent architecture with a Memorizer and Researcher, combining lightweight memory with a full page-store for just in time context construction.
Deep research over complete history
GAM formalizes Planning, Searching, Integration, and Reflection in the Researcher, enabling iterative deep research guided by pre-constructed memory and multiple search tools.
Unified end to end optimization
GAM defines a reinforcement learning objective over Memorizer and Researcher, optimizing expected reward R with policy gradients ∇θm and ∇θr on memory grounded tasks.
RESULTS
RULER Retri. Acc.
97.70
+3.45 over RAG
HotpotQA 56K F1
64.07
vs LONG-LLM 49.75 on HotpotQA 56K
LoCoMo Single Hop F1
57.75
+11.07 over RAG on GPT-4o-mini
HotpotQA 56K build time
56.89 s
offline build vs A-mem 209.74 s on HotpotQA 56K
These numbers come from LoCoMo, HotpotQA, and RULER 128K, which test long-term conversational memory, multi-hop QA, and long-context retrieval. MAIN_RESULT shows that GAM converts full histories into high-utility contexts more accurately and efficiently than static memory systems like RAG and A-MEM.
BENCHMARK
These numbers come from LoCoMo, HotpotQA, and RULER 128K, which test long-term conversational memory, multi-hop QA, and long-context retrieval. MAIN_RESULT shows that GAM converts full histories into high-utility contexts more accurately and efficiently than static memory systems like RAG and A-MEM.
BENCHMARK
F1 score on HotpotQA 56K long-context question answering benchmark.
BENCHMARK
Total time in seconds on HotpotQA 56K including offline build and online serve.
KEY INSIGHT
On RULER multi hop tracing, GAM reaches 93.20% accuracy with GPT-4o-mini, while RAG collapses to 0.00% despite using the same backbone.
This is surprising because many assume stronger retrieval alone suffices, but GAM shows that agentic planning and reflection over a page-store are crucial for complex long-context reasoning.
WHY IT MATTERS
GAM unlocks general agentic memory where agents can JIT-compile optimized contexts from complete histories using deep research rather than static compression.
Builders can now design agents that scale test-time computation, planning, and search depth to match task difficulty, instead of being bottlenecked by fixed context windows or lossy summaries.
Nikhil Verma
· 2026
Focus Agent adds start_focus, complete_focus, a persistent Knowledge block, and an optimized Persistent Bash plus String-Replace Editor scaffold to actively compress context during long software-engineering tasks. On five hard SWE-bench Lite instances against a Baseline ReAct agent, Focus Agent achieves 22.7% token reduction (14.9M → 11.5M) while matching 3/5 = 60% task success.
Xiaohui Zhang, Zequn Sun et al.
· 2026
ActMem transforms dialogue history into atomic facts via Memory Fact Extraction, groups them with Fact Clustering, links them through a Memory KG Construction module, and uses Counterfactual-based Retrieval and Reasoning for action-aware answers. On ActMemEval, ActMem reaches 76.52% QA accuracy with DeepSeek-V3, beating LightMem’s 63.97% by 12.55 points and NaiveRAG’s 61.54%.
Xingyu Lyu, Jianfeng He et al.
· 2026
ADAM combines Anchor extraction, Distribution estimation, Anchor selection, and Query generation to adaptively probe agent memory via an auxiliary generator and entropy based selection. On the EHRAgent benchmark with Llama2-7b-chat, ADAM reaches EQ=77 and ASR=1.00, compared to MEXTRA’s EQ=44 and ASR=0.89.
Answers use this explainer on Memory Papers.
Checking…