A leaderboard is a screening tool, not a model approval.

Total Recall at What Cost? Benchmarking the Serving Cost of Agentic Memory Systems

New research benchmarks the serving costs of agentic memory frameworks against standard context window strategies over long conversations.

From Numbers to Judgment: Specialist LLM Agents and Reinforcement Learning for European Listed Real Estate

Research shows specialist agent decomposition outperforms monolithic LLM prompting in complex European listed real estate financial analysis.

GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation

Researchers applied GRPO reinforcement learning to fine-tune an LLM for financial advice, reportedly beating frontier commercial models.

Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents

Research proposes trajectory-adapted uncertainty quantification for LLM agents to track multi-step error propagation across tool calls.

TradingMoE: Routing the Right Experts in Evolving Markets

Researchers introduce TradingMoE, a Mixture-of-Experts routing framework designed for LLM-based trading across changing market conditions.

Long-Horizon Forecasting of Complete Financial Statements with Forma