arXiv cs.CL· Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zirui Zhou·· 10 小时前AI 评分34
HEDGE:面向可扩展多智能体辩论的门控超图记忆框架
HEDGE: Gated Hypergraph Memory for Scalable Multi-Agent Debate
AI 导读
HEDGE 是一个选择性记忆框架,将多智能体辩论轨迹表示为语义超图,并用学习式记忆选择模块(MSM)把每个记忆候选路由到 STORE、BACKUP 或 OMIT。在七个基准上,HEDGE 平均比最强的多智能体系统(基于 GPT-4o-mini)准确率高出 5.0 分,冲突密集任务上提升达 8.2 分,同时记忆占用减少 48%、辩论轮数减少 34%。代码已开源。
正文 · 原文
Abstract:Multi-agent debate systems require agents to retain and revisit arguments across multiple rounds, yet limited context windows and unstructured memories make relevant information increasingly difficult to recover. Existing flat and pairwise-graph memories also struggle to capture higher-order relations, including multi-agent agreement, conflicting evidence, and evolving consensus. We introduce HEDGE, a selective memory framework that represents debate trajectories as semantic hypergraphs. Hyperedges connect related claims across agents, while intra-hyperedge relational graphs preserve fine-grained argumentative structure. A learned memory selection module (MSM), trained through supervised learning and reinforcement learning, routes each memory candidate to STORE, BACKUP, or OMIT, retaining useful information while limiting redundancy. Across seven diverse benchmarks, HEDGE consistently outperforms strong single-agent, multi-agent, and memory baselines, improving accuracy by 5.0 points on average over the strongest multi-agent system with GPT-4o-mini. The gains reach 8.2 points on conflict-heavy tasks, while HEDGE reduces memory usage by 48% and the number of debate rounds by 34%. Code is available at: this https URL.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.38902 [cs.CL] |
| (or arXiv:2610.38902v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38902 arXiv-issued DOI via DataCite |
Submission history
From: Amirhossein Abaskohi [view email]
[v1]
Wed, 28 Oct 2026 20:57:59 UTC (2,666 KB)
[v2]
Wed, 18 Nov 2026 20:55:36 UTC (2,668 KB)
来源:arXiv cs.CL · arxiv.org