FIRME is a registry‑anchored memory graph designed to integrate investor knowledge across multiple sources and time periods while preserving identity, provenance, and context. It reconciles varying surface forms of observations into canonical relationships, fuses investor‑call discussions with portfolio cash‑flow signals within periods, and uses persistent aliases to maintain consistent relationship histories across periods. Evaluation on proprietary investor‑call data and S&P 500 earnings‑call transcripts shows significant improvements in Correct Match Rate and reattachment‑recall compared to a baseline registry.
By Yunbai Zhang, Yunyi Gao, Han-Tai Shiao
FinMultiHopQA is a new benchmark comprising 15,600 financial questions that require multi‑hop reasoning across filing sections, fiscal years, and peer companies. It is grounded in FinReflectKG, a temporally indexed financial knowledge graph with over 17.5 million triples derived from SEC 10‑K filings. The benchmark uniquely supports controlled multi‑hop taxonomies, document topologies, motif‑level reproducibility, and provenance‑linked auditability, and it allows researchers to test how different evidence presentations affect large language model performance.
By Abhinav Arun, Reetu Raj Harsh, Bhaskarjit Sarmah, Stefano Pasquali
arXiv:2602. 07294v4 Announce Type: replace-cross Abstract: With the increasing deployment of Large Language Models (LLMs) in the finance domain, LLMs are increasingly expected to parse complex regulatory disclosures.
By Yidong Jiang, Junrong Chen, Eftychia Makri, Jialin Chen, Peiwen Li, Ali Maatouk, Leandros Tassiulas, Eliot Brenner, Bing Xiang, Rex Ying
arXiv:2605. 27864v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied in finance, yet most existing work emphasizes trading signals or financial NLP tasks centered on prediction.
By Di Zhu, Lei Nico Zheng, Zihan Chen
arXiv:2608.24842v1 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly deployed as AI analysts to process financial disclosures and support AI-assisted investment decisions....
By Miao Liu, Zhizhe Liu
Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memories as independent evidence and combine them through voting or weighting.
AnalysisBank is a library that captures expert financial analysis by pairing data signals with analytical moves and the corresponding expert text spans. The system matches input signals to these library entries during inference, enabling the generation of reports that are grounded in data-derived insights rather than generic structural templates. Experiments on financial benchmarks show that AnalysisBank produces 1.7–3.7 times more novel, data‑grounded insights than structural baselines, and the approach also transfers to scientific writing.
By Yajing Yang, Yunshan Ma, Kelvin J. L. Koa, Min-Yen Kan
arXiv:2606. 01886v1 Announce Type: new Abstract: Financial AI agents often fail for a simple reason: they make users carry the complexity.
By Ailiya Borjigin, Igor Stadnyk, Ben Bilski, Maksym Chikita, Dmytro Kyrylenko, Sofiia Pidturkina, Julia Stadnyk
DiRAFT is a method for generating privacy‑aware financial transcripts by extracting concept graphs from customer conversations and sampling new graph plans from aggregate transition, starting‑concept, and plan‑length priors. The approach uses a discourse layer to realize text without referencing individual source passages, aiming to preserve discourse fidelity while reducing residual confidentiality risks. The authors evaluate privacy through corpus‑level structural overlap and source‑grounded checks for non‑public investor facts, finding that stochastic sampling yields lower structural overlap and fewer confidential fact matches compared to greedy or top‑3 strategies.
By Yunbai Zhang, Yunyi Gao, Han-Tai Shiao
arXiv:2608. 10509v1 Announce Type: new Abstract: Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or action.
By Yiqi Wang, Zihao Yan, Jiaqi Zhang, Zhangkai Wu, Mingkai Zheng, Zequn Sun, Yanming Zhu, Taotao Cai
arXiv:2605.27864v5 Announce Type: replace
Abstract: Large language models (LLMs) are increasingly applied in finance, yet most existing work emphasizes trading signals or financial NLP tasks centered...
By Di Zhu, Lei Nico Zheng, Zihan Chen
EvolveTrade is a self‑evolving framework that treats the system prompt of a tool‑using LLM trading agent as a text‑parameterized policy. After each update interval, a Policy Agent revises this policy using accumulated decision traces and portfolio feedback while keeping the backbone LLM fixed, allowing the agent to refine its information‑acquisition and portfolio‑construction procedures over time. Experiments across multiple market regimes and two LLM backbones show that EvolveTrade often improves Sharpe Ratio and Cumulative Return over fixed‑policy baselines, with behavioral analyses indicating increased code‑mediated analysis and regime‑relevant computations.
By Sehee Kim, Yumin Choi, Minki Kang, Sung Ju Hwang