OpenFinGym is a multi-task verifiable gym environment for quant-finance agents with automated task construction from publications, containerised runtime, paper trading engine, and support for SFT/RL training.
hub Canonical reference
PIXIU: A large language model, instruction data and evaluation benchmark for finance
Canonical reference. 80% of citing Pith papers cite this work as background.
22
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
FlexServe introduces recallable secure memory and NPU to enable cooperative secure LLM inference on mobile devices, reporting 10.05X TTFT speedup over a basic TrustZone strawman.
LLMs copy biased analyst ratings in investment decisions but a new detection method encourages independent reasoning and can improve stock return predictions beyond human levels.
Constrained LLM agents discover cryptocurrency factors that produce a portfolio with 44.55% annualized return and Sharpe ratio of 1.55 in pure out-of-sample 2024-2026 testing after trading costs.
SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 models in 6 scenarios.
FinAuditing is a taxonomy-structured multi-document benchmark with 1,102 instances averaging over 33k tokens from XBRL filings, defining three tasks to evaluate LLMs on financial auditing capabilities.
FinTagging decomposes XBRL tagging into FinNI extraction and FinCL full-taxonomy linking, showing LLMs handle extraction but struggle with fine-grained concept alignment in zero-shot settings.
Page-granular Flex-Mem and switchable Flex-NPU cut TrustZone LLM TTFT by ~10× vs a CMA strawman and ~2.4× vs a pipelined secure-NPU strawman on RK3588.
CLExEval introduces a human-annotated evaluation framework on 40 rare cases that identifies verbosity bias, hidden knowledge paradox, and 68.6% reasoning-to-output mismatch in LLMs while showing LLM-as-a-Judge overestimates reliability.
FINESSE-Bench is a new hierarchical benchmark suite combining certification-style exams, trading tasks, and a Russian olympiad set to evaluate LLMs on financial competencies at multiple difficulty levels.
LLM filtering of embedding-based stock networks raises long-short Sharpe ratio from 0.742 to 0.820 and cuts max drawdown from -10.47% to -7.85% in 2011-2019 S&P 500 backtests.
MFMDQwen is the first open-source LLM for multilingual financial misinformation detection, backed by a new instruction dataset and benchmark on which it outperforms other open-source models.
SysTradeBench evaluates 17 LLMs on 12 trading strategies, finding over 91.7% code validity but rapid convergence in iterative fixes and a continued need for human oversight on critical strategies.
AgenticEval is a multi-agent framework that ingests unstructured policies to generate and self-evolve comprehensive safety benchmarks for LLMs, with experiments showing declining safety rates as tests harden.
A survey proposing a taxonomy of Injective, Bridging, and Internal Alignment paradigms to evolve TSA into user-driven Time Series Question Answering with LLMs.
A deep-RL portfolio system with ticker-agnostic encoding, six-objective MoE policy, and LoRA personalization reports +2.93% 14-day alpha vs equal-weight, but the evidence is a short, in-sample, cost-free backtest.
MoCA-Agent decomposes questions into typed atomic claims, clears them via trader-agent markets into confidence-weighted decisions, synthesizes and verifies executable Python code, and reports strong benchmark scores including 78.3% on FinQA.
DarkForest improves multi-agent LLM reasoning via independent agents, semantic clustering of responses, and calibrated belief estimation with controlled communication, yielding up to 30.7% better benchmark metrics and 6.5x lower token consumption than heavy-communication baselines.
Strat-LLM demonstrates that LLM trading performance varies by reasoning mode and model scale, with strict alignment reducing drawdowns in downtrends and deep reasoning avoiding small-gain traps.
CausalGAN + SAC RL pipeline generates synthetic bond yield data; fine-tuned Qwen2.5-7B LLM produces trading signals, with reported MAE 0.103, 60% profit rate, and LLM score 3.37/5.
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
A survey synthesizing recent LLM research and assessing its applicability to financial data analysis.
citing papers explorer
-
OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents
OpenFinGym is a multi-task verifiable gym environment for quant-finance agents with automated task construction from publications, containerised runtime, paper trading engine, and support for SFT/RL training.
-
FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
FlexServe introduces recallable secure memory and NPU to enable cooperative secure LLM inference on mobile devices, reporting 10.05X TTFT speedup over a basic TrustZone strawman.
-
Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain
LLMs copy biased analyst ratings in investment decisions but a new detection method encourages independent reasoning and can improve stock return predictions beyond human levels.
-
From Hypotheses to Factors: Constrained LLM Agents in Cryptocurrency Markets
Constrained LLM agents discover cryptocurrency factors that produce a portfolio with 44.55% annualized return and Sharpe ratio of 1.55 in pure out-of-sample 2024-2026 testing after trading costs.
-
SAGE: A Service Agent Graph-guided Evaluation Benchmark
SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 models in 6 scenarios.
-
FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs
FinAuditing is a taxonomy-structured multi-document benchmark with 1,102 instances averaging over 33k tokens from XBRL filings, defining three tasks to evaluate LLMs on financial auditing capabilities.
-
FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information
FinTagging decomposes XBRL tagging into FinNI extraction and FinCL full-taxonomy linking, showing LLMs handle extraction but struggle with fine-grained concept alignment in zero-shot settings.
-
FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
Page-granular Flex-Mem and switchable Flex-NPU cut TrustZone LLM TTFT by ~10× vs a CMA strawman and ~2.4× vs a pipelined secure-NPU strawman on RK3588.
-
CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning
CLExEval introduces a human-annotated evaluation framework on 40 rare cases that identifies verbosity bias, hidden knowledge paradox, and 68.6% reasoning-to-output mismatch in LLMs while showing LLM-as-a-Judge overestimates reliability.
-
FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models
FINESSE-Bench is a new hierarchical benchmark suite combining certification-style exams, trading tasks, and a Russian olympiad set to evaluate LLMs on financial competencies at multiple difficulty levels.
-
Cross-Stock Predictability via LLM-Augmented Semantic Networks
LLM filtering of embedding-based stock networks raises long-short Sharpe ratio from 0.742 to 0.820 and cuts max drawdown from -10.47% to -7.85% in 2011-2019 S&P 500 backtests.
-
MFMDQwen: Multilingual Financial Misinformation Detection Based on Large Language Model
MFMDQwen is the first open-source LLM for multilingual financial misinformation detection, backed by a new instruction dataset and benchmark on which it outperforms other open-source models.
-
SysTradeBench: An Iterative Build-Test-Patch Benchmark for Strategy-to-Code Trading Systems with Drift-Aware Diagnostics
SysTradeBench evaluates 17 LLMs on 12 trading strategies, finding over 91.7% code validity but rapid convergence in iterative fixes and a continued need for human oversight on critical strategies.
-
AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
AgenticEval is a multi-agent framework that ingests unstructured policies to generate and self-evolve comprehensive safety benchmarks for LLMs, with experiments showing declining safety rates as tests harden.
-
From Time Series Analysis to Question Answering: A Survey in the LLM Era
A survey proposing a taxonomy of Injective, Bridging, and Internal Alignment paradigms to evolve TSA into user-driven Time Series Question Answering with LLMs.
-
A Three-Phase Foundation Model for Tax-Aware Personalized Portfolio Management
A deep-RL portfolio system with ticker-agnostic encoding, six-objective MoE policy, and LoRA personalization reports +2.93% 14-day alpha vs equal-weight, but the evidence is a short, in-sample, cost-free backtest.
-
MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning
MoCA-Agent decomposes questions into typed atomic claims, clears them via trader-agent markets into confidence-weighted decisions, synthesizes and verifies executable Python code, and reports strong benchmark scores including 78.3% on FinQA.
-
DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs
DarkForest improves multi-agent LLM reasoning via independent agents, semantic clustering of responses, and calibrated belief estimation with controlled communication, yielding up to 30.7% better benchmark metrics and 6.5x lower token consumption than heavy-communication baselines.
-
Strat-LLM: Stratified Strategy Alignment for LLM-based Stock Trading with Real-time Multi-Source Signals
Strat-LLM demonstrates that LLM trading performance varies by reasoning mode and model scale, with strict alignment reducing drawdowns in downtrends and deep reasoning avoiding small-gain traps.
-
Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation
CausalGAN + SAC RL pipeline generates synthetic bond yield data; fine-tuned Qwen2.5-7B LLM produces trading signals, with reported MAE 0.103, 60% profit rate, and LLM score 3.37/5.
-
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
-
Bridging Language Models and Financial Analysis
A survey synthesizing recent LLM research and assessing its applicability to financial data analysis.