On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “DeepSeek-R1”

Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statisticcs.LG

Unified framework for understanding GRPO as U-statistic.

problem Theoretical properties of GRPO remain less studied.

method Unified framework through classical U-statistics.

result GRPO is asymptotically equivalent to an oracle policy gradient algorithm.

Group Relative Policy Optimization U-statistic Policy Gradient DeepSeekMath DeepSeek-R1

2026-03-01abs ↗pdf ↗

Reliable Decision Support with LLMs: A Framework for Evaluating Consistency in Binary Text Classification Applicationscs.CL

Study evaluates consistency of LLMs in binary text classification, providing systematic guidance.

problem Lack of reliable methods for evaluating large language model (LLM) binary text classification.

method Adapting psychometric principles, the study determines sample size requirements, develops metrics for invalid responses, and evaluates intra- and inter-rater reliability.

result LLMs demonstrated high intra-rater consistency, achieving perfect agreement on 90-98% of examples, with smaller models outperforming larger counterparts.

large language models binary text classification reliability assessment sample size planning financial news sentiment

2025-05-20abs ↗pdf ↗

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforcecs.LG

A minimalist approach improves LLM reasoning by filtering incorrect responses.

problem Improving large language model (LLM) reasoning on complex tasks.

method Revisit GRPO from a reinforce-like algorithm perspective, proposing Reinforce-Rej.

result RAFT, a simple rejection sampling baseline, outperforms GRPO and PPO.

large language models reinforcement learning policy gradient rejection sampling negative samples

2025-04-15abs ↗pdf ↗

Understanding the Role of Training Data in Test-Time Scalingcs.AI

The study examines how extra compute during testing affects the performance of large language models.

problem Understanding the conditions under which test-time scaling improves model performance.

method An in-context weight prediction task for linear regression was used to train transformers. The performance was analyzed under varying levels of test-time compute.

result Training transformers on diverse, relevant, and hard tasks leads to the best performance for test-time scaling.

test-time scaling large language models transformers linear regression context length

2025-10-04abs ↗pdf ↗

Design and Empirical Study of a Large Language Model-Based Multi-Agent Investment System for Chinese Public REITsq-fin.ST

Study proposes a multi-agent system using LLMs for REIT trading, outperforming benchmarks.

problem Low-volatility Chinese REIT market, low risk-adjusted returns.

method Multi-agent framework with four types of agents, prediction model pathways, fine-tuning.

result Multi-agent strategies outperform buy-and-hold in terms of return, Sharpe ratio, and drawdown.

REITs Real Estate Investment Trusts Multi-Agent System Large Language Models Trading Strategies

2026-01-22abs ↗pdf ↗

Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Modelscs.CL

Painless Activation Steering automates post-training for LMs without manual intervention.

problem Manual post-training methods are time-consuming and labor-intensive.

method Painless Activation Steering (PAS) is a fully automated approach that requires no manual intervention.

result PAS reliably improves performance for behavior tasks but not for intelligence-oriented tasks.

activation steering post-training language models automation behavior tasks

2025-09-25abs ↗pdf ↗