The paper proposes the Interaction-Native Knowledge Harness (InKH), an architecture that absorbs complex context into financial LLM agents, significantly improving performance, reducing latency, and e…

The paper introduces FinBoardBench, a novel evaluation suite using financial board games to demonstrate that current LLMs, despite strong static reasoning, fail at complex, dynamic wealth management a…

The paper introduces BlueFin, a challenging benchmark for evaluating LLM agents on complex financial spreadsheet tasks, finding that even frontier models perform poorly, scoring less than 50% on avera…

The paper introduces PortBench, a comprehensive benchmark that evaluates LLMs for portfolio management by assessing both correlation awareness and performance across a full, multi-stage decision pipel…

This paper proposes a unified, lifecycle-centric framework and a detailed taxonomy to survey and analyze novel, finance-specific attack surfaces and vulnerabilities in AI systems used within the finan…

FundaPod is a multi-persona agent platform designed for fundamental investment research, enabling AI agents with distinct viewpoints to independently gather evidence and surface disagreements for huma…

The paper demonstrates that large language models (LLMs) exhibit measurable, controllable biases toward specific assets like Bitcoin, identifying an internal feature that can causally shift portfolio…

The paper proposes ReCAP, a novel continual learning framework for portfolio management, which adaptively combines policies from a library based on detected market regimes to achieve superior long-ter…

The paper analyzes the nascent DeFi investment agent market, finding that while token valuations are high, current deployments are heterogeneous, lack clear autonomous execution, and exhibit poor risk…

The paper empirically analyzes the nascent DeFi investment agent market, finding that while token valuations are high, current deployments lack robust autonomous execution and exhibit poor risk-adjust…

The paper simulates bargaining scenarios using LLM agents to analyze how optimizing agents for financial profit affects their honesty and trust, finding that while fine-tuning improves deal-making, it…

The paper proposes an infrastructure, clawgang and meowtrade, to transform private, non-transferable agent memories into verifiable, tradable economic commodities.

This paper introduces CFMME, a comprehensive Chinese financial multimodal benchmark, and evaluates current Large Vision-Language Models (LVLMs), finding that while state-of-the-art models perform mode…

The paper introduces AGENTCL, a rigorous evaluation framework that uses controlled task streams to accurately measure an agent's ability to accumulate and reuse knowledge across multiple tasks, thereb…

The paper introduces ForesightFlow, an Information Leakage Score (ILS) framework, to quantify pre-event information leakage in prediction markets, and proposes a necessary extension to analyze empiric…

The paper introduces ForeSci, a novel benchmark that evaluates LLM agents' ability to make forward-looking research judgments using only historical evidence, finding that explicit evidence organizatio…

This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a signific…

The paper proposes a market-feedback adaptive retrieval system for frozen LLMs in financial RAG, significantly improving event-impact prediction by learning which evidence sources to prioritize.

The paper evaluates multi-agent LLM oracle systems for prediction market resolution, finding that independent aggregation with confidence-weighted voting significantly outperforms single-model baselin…

The paper argues that current search agents often verify existing knowledge rather than genuinely searching, and introduces LiveBrowseComp, a new benchmark to measure true evidence-driven discovery.