跳到正文
Jones Ray

ScholarPulse 日报 2026-09-20

2026-09-20 学术简报:2 篇。该工作提出人在环、物理约束多智能体流程,自动化并审计理论到求解器建模,用于吸力沉箱土塞演化。

今日速览

序号标题来源日期主题推荐等级
1Human-guided physics-constrained AI agents construct an auditable model of soil-plug evolutionarXiv2026-09-20AI-Agent高
2Graph Memory for LLM Agents: At What Cost? A Comparative Evaluation of Query, Ingest, and Update Performance Across Graph Database EnginesarXiv2026-09-20AI-Agent高

重点论文与技术动态

1. Human-guided physics-constrained AI agents construct an auditable model of soil-plug evolution

一句话结论

该工作提出人在环、物理约束多智能体流程,自动化并审计理论到求解器建模,用于吸力沉箱土塞演化。

核心内容

方法与数据

价值判断

摘要 Engineering predictions require physical mechanisms to be translated consistently into equations, discretization, code, and validation, yet errors can propagate despite local checks. Artificial-intelligence (AI) agents automate scientific tasks, but coordinating and independently auditing the theory-to-solver process under physical constraints and human oversight remains unresolved. We introduce a human-in-the-loop, physics-constrained multi-agent workflow where human experts define admissible physics and modeling boundaries, while agents retrieve evidence, derive equations, implement solvers, and audit the theory-to-code chain. Applied to soil-plug evolution during suction-caisson installation, the workflow generated and audited 6 formulations in 2.9 h of agent execution once physical knowledge and inputs were prepared. Among these formulations, adding seepage-driven soil void-ratio evolution to the geometric baseline reduced mean absolute final-heave error from 58.4% to 9.0% across 14 profiles; the selected model further incorporated near-wall dilation and achieved mean absolute percentage errors of 12.4% across 9 final-state cases and 4.2% at the endpoints of 5 process histories. Beyond predictive performance, blinded replay recovered all 9 target problems, while an independent audit uncovered 5 implementation problems after 36 predefined checks had passed. Overall, this work extends multi-agent AI beyond task automation toward human-governed engineering solvers.

2. Graph Memory for LLM Agents: At What Cost? A Comparative Evaluation of Query, Ingest, and Update Performance Across Graph Database Engines

一句话结论

该研究以合成生物医学属性图和20类查询比较8种图数据库/引擎,发现没有绝对最快系统,总成本主要由批量摄取吞吐决定。

核心内容

方法与数据

价值判断

摘要 Graph databases are frequently positioned as categorically necessary for connected-data workloads, yet the systems dimension along which they actually differ - query planning, indexing, and data-readiness cost - is rarely isolated from vendor framing. We construct a synthetic, biomedical-shaped property graph (1.02 million nodes, 5.34 million total node and edge rows) and a twenty-query workload spanning neighborhood lookups, bounded paths, set intersections, anti-joins, grouped aggregation, top-k ranking, temporal filters, full scans, and relational joins. We benchmark Corvic AI - a purpose-built columnar query engine underlying Corvic's ontology management layer ("memories")- against seven purpose-built or graph-extension database systems (LoraDB, Ladybug, DuckPGQ, Memgraph, Neo4j, HugeGraph, and FalkorDB) at three graph scales spanning three orders of magnitude. We report query latency geomeans, bulk-ingest throughput, point-update latency, and answer correctness for each system, and we derive a simple total-cost-of-ownership model that expresses the ingest/query trade-off as a function of query volume. Our central finding is that no system in this sample is categorically fastest: a native graph engine (Ladybug) outperforms Corvic AI on narrow, bounded-neighborhood shapes, while Corvic AI is faster on shapes that scan or join a large fraction of the graph, and a system implementing graph query syntax via SQL/PGQ (DuckPGQ) is measurably slower purely due to query-plan choice. The dominant cost differential in our data is not query latency but the cost of making data queryable at all: bulk-ingest throughput varies by three orders of magnitude across engines (5.0k-4.3M rows/s), a gap that a simple crossover-point calculation shows dominates total cost for any workload with fewer than roughly 105 queries per data refresh.