Quantitative strategy optimization remains largely manual, requiring domain experts to identify weak signals, tune risk-control rules, and repeatedly validate iterative revisions. Large language models can accelerate this process, but directly relying on them to rewrite trading strategies often introduces hallucinated edits, strategy drift, and back-test overfitting. We propose EVOQUANT, a self-evolving verifier-guided framework for strategy optimization in quantitative trading. Our method utilizes LLMs to deeply diagnose performance bottlenecks, generate semantically controlled candidate edits, select the best strategy through a multi-stage verification pipeline, and distill optimization experience into reusable knowledge for continual self-improvement. We evaluate our method using seven representative strategies: four from the A-share market and three from the crypto market. Experimental results show that our method significantly improves the Sharpe ratio across all tested strategies: the average test Sharpe increases from −0.298 to 0.538, and the best-performing strategy achieves a 199% relative improvement. Ablation studies and stress tests under stricter conditions further validate the effectiveness and robustness of the framework. Overall, this work transforms quantitative strategy optimization from costly manual trial-and-error into an automated and verifiable iterative paradigm, offering a new path for applying large language models to financial strategy research.

Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing evaluations typically report performance metrics, but rarely examine agentic viability: whether dynamic LLM-mediated decisions convert their induced costs into measurable incremental profit. To apply this criterion, we introduce TradeLens, a trace-grounded diagnostic toolkit for evaluating agentic trading systems from their trading records, runtime traces, and deployment configurations. It reconstructs trading trajectories, attributes profit and cost to interpretable evidence, and diagnoses whether and why an agent pays for its own intelligence. We conduct extensive analysis across backbone models, capital scales, trading frequencies, and system architectures, together with deployment discussion. Our results show that viability hinges on intelligence-to-profit conversion: models exhibit different failure patterns, such as poor asset selection in DeepSeek-V3.2 and negative timing in GLM-4.7, while capital scale, trading frequency, and architecture matter primarily in these runs, especially through their effects on decision-attributed timing value. These findings reframe the evaluation of LLM-based trading agents from capability-centric performance ranking to trace-grounded diagnosis of intelligence-to-profit conversion. Our code is available at https://github.com/ParadooxAI/TradeLens.

Large language models (LLMs) are increasingly used to explain numerical time series, but fluent explanations can misstate when a change occurs, overstate a trend, or introduce unsupported patterns. Existing evaluations often score forecasts, answers, or whole explanations, leaving claim-level temporal grounding undermeasured. We introduce TimeClaimBench, a benchmark that parses explanations into atomic temporal claims and verifies them against a deterministic extracted event graph. Across five LLMs on controlled synthetic series, event-grounded prompting raises the strict graph-supported rate by 18.3 points and reduces graph-unsupported claims by 27.9 points under this fixed operational criterion. Calibration analyses show the boundary of that result. The extractor recovers the designed primary event in 394 of 400 series, but this does not estimate the precision of additional extracted events. A blinded two-annotator comparison on one model and 40 series reverses the automatic ordering: holistic ratings favor Direct and chain-of-thought outputs over event-grounded outputs. therefore distinguishes four axes that should not be conflated: designed-event recovery, the unresolved precision of additional events, claim-to-graph consistency, and whole-explanation human judgment. Code: https://github.com/lunaaa95/TimeClaimBench