QuantEvolver applies reinforcement fine-tuning to evolve an LLM policy for generating executable alpha factor expressions, yielding higher-quality and more complementary factors than prompt-based baselines on market benchmarks.
Deep reinforcement learning from human preferences
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Introduces the first benchmark for fine-grained failures in reinforcement fine-tuning of LLMs and an automatic management framework that detects, diagnoses, and remediates them.
VL-DPO uses a VLM as a zero-shot reasoner to generate preference pairs from pretrained model rollouts, then finetunes via DPO on the Waymo Open End-to-End Driving Dataset, yielding 11.94% higher rater feedback score and 10.01% lower average displacement error.
SPLC uses social preference feedback to auto-generate preference data for offline RL, improving socially compliant crowd robot navigation over baselines.
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.
citing papers explorer
-
From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery
QuantEvolver applies reinforcement fine-tuning to evolve an LLM policy for generating executable alpha factor expressions, yielding higher-quality and more complementary factors than prompt-based baselines on market benchmarks.
-
Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning
Introduces the first benchmark for fine-grained failures in reinforcement fine-tuning of LLMs and an automatic management framework that detects, diagnoses, and remediates them.
-
VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving
VL-DPO uses a VLM as a zero-shot reasoner to generate preference pairs from pretrained model rollouts, then finetunes via DPO on the Waymo Open End-to-End Driving Dataset, yielding 11.94% higher rater feedback score and 10.01% lower average displacement error.
-
SPLC: Social Preference Learning for Crowd Robot Navigation
SPLC uses social preference feedback to auto-generate preference data for offline RL, improving socially compliant crowd robot navigation over baselines.
-
Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.