arXiv:2609.08599v1 Announce Type: new Abstract: Large Language Model (LLM) agents are evolving from single-session tools toward long-term personal assistants that must adapt to individual users acros...
arXiv:2607. 04617v1 Announce Type: new Abstract: Long-lived AI agents require continuity across interactions, but continuity cannot be obtained by simply extending the prompt window.
Long-lived AI agents require continuity across interactions, but continuity cannot be obtained by simply extending the prompt window. An agent must preserve useful prior experience, retrieve it selectively, distinguish personal context from external evidence, and revise memory when the underlying situation changes.
arXiv:2608. 11248v1 Announce Type: new Abstract: Long-term memory is essential for language agents operating across extended interactions and evolving tasks.
EdgeMem is a new agent-memory method that preserves original interaction turns and organizes them using complementary content, temporal, and episodic cues via a multi‑anchor hypergraph. It performs lightweight local processing, returning source evidence directly and reserving LLM use only for final answer generation. Experiments on LoCoMo and LongMemEval‑S demonstrate strong retrieval and memory‑grounded question answering, with EdgeMem achieving the highest strict‑judge score among seven systems on LoCoMo while requiring no generative‑LLM calls for construction and retrieval.
PGMem introduces a persona‑memory graph that tightly couples user persona signals with the events that support or revise them, using typed provenance and evidence edges. This design addresses gaps in existing memory systems where personas are stored as flat, detached profiles. Experiments on three benchmarks show that PGMem outperforms various baseline memory approaches, especially as dialogue context length increases.
arXiv:2606. 07909v1 Announce Type: new Abstract: Modern large language model (LLM) agents can use external tools to help users solve complex tasks.
arXiv:2606. 07909v2 Announce Type: replace Abstract: Modern large language model (LLM) agents can use external tools to help users solve complex tasks.
arXiv:2608. 05095v1 Announce Type: new Abstract: Agents for long term reasoning require a memory that can be efficiently and effectively updated over time, as new facts and external feedback continue to arrive.
arXiv:2607. 05794v1 Announce Type: new Abstract: Long-term user memory is essential for personalized conversational agents, yet many memory systems still expose memory through passive retrieval interfaces, making the model a consumer of pre-selected evidence.
arXiv:2607. 20482v1 Announce Type: new Abstract: Recent advances in large language models have enabled web agents to autonomously execute complex tasks.
The paper introduces StructMemEval, a benchmark designed to assess how well large language model (LLM) agents can organize their long‑term memory rather than merely recall facts. It compiles tasks that humans typically solve by structuring knowledge—such as transaction ledgers, to‑do lists, and trees—and evaluates agents on these. Experiments show that simple retrieval‑augmented LLMs struggle with such organization tasks, while memory‑augmented agents perform better when explicitly prompted to structure their memory, yet many modern LLMs still fail to recognize memory structures without prompting.