← Back to all news
arXiv Computation and Language By Chongyuan Dai, Yaling Shen, Zirui Song, Junfeng Liao, Jinpeng Hu, Xiuying Chen

Twists and Turns: A Graph-Based Benchmark and Framework for Long-Term Memory in Exploration Tasks

Read the original on arXiv Computation and Language →

The paper introduces “LExMem”, a graph‑guided benchmark that evaluates long‑term memory in exploration tasks by modeling these processes as evolving graphs and generating 224 dialogues with 2,018 question‑answer pairs. It also presents “LExGraph”, a graph‑based memory framework that incrementally organizes dialogues into interconnected nodes and retrieves evidence via hybrid retrieval and neighbor expansion. Experiments show that “LExMem” challenges existing systems, while “LExGraph” outperforms them and generalizes to external benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Aug 19

G-ReAct: Graph-Guided Deep Search via Structure-State Co-Evolution

G-ReAct is a reasoning framework that frames deep search as state evolution over a fixed-topology query graph, enabling explicit tracking of search progress and constraint preservation. It generates high-quality trajectories for fine-tuning and provides structured guidance during inference without extra fine-tuning. Experiments show that with only 1.9K generated trajectories, a Qwen3 model achieves strong accuracy on BrowseComp-ZH and XBench, outperforming larger open-source baselines, and consistently improves existing LLMs on deep-search tasks.

By Shaoxiong Yang, Mengyuan Zhang, Shaojun Lin, Chao Li, Wei Liu, Kun Shao, Jian Luan
llmsreinforcement-learningfine-tuning
More like this →
arXiv AI
Sep 10

When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agents

The paper introduces MERIT, a benchmark that evaluates the marginal benefit of long‑term memory for tool‑using large language model agents while explicitly accounting for cost. MERIT provides episodic tool‑use tasks across three domains, verifies dependence on earlier‑episode facts, and measures memory operations in tokens and dollars. Experiments on GPT‑4.1‑mini, Claude Haiku 4.5, and Claude Sonnet 5 show that memory can significantly improve task success, but its utility varies widely across models and memory implementations, and full replay is rarely cost‑effective.

By Shweta Mishra, Shashank Mishra
llmsragagentsnlpbenchmarks
More like this →