Research
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.

168,695 papers · 148 categories

Trend · papers per month

1223 · Mar 202619922001200920172026
30 results for Self-improvement

The paper develops a theory for iterative self-improvement of models, proving conditions for better performance with easy-to-hard curricula.

problem Lack of theoretical foundation for iterative self-improvement in practical settings.
method Modeling self-improvement as maximum-likelihood fine-tuning on reward-filtered distributions and proving finite-sample guarantees.
result Explicit feedback loop and conditions for better performance with easy-to-hard curricula.

SRPO improves AI alignment with human preferences through self-improvement and task-independent optimization.

problem AI models trained with RLHF lack self-correction mechanisms and struggle with task generalization.
method SRPO formulates the preference learning problem as a min-max objective, optimizing a self-improvement policy and a generative policy in an adversarial fashion, making the solution task-independent.
result SRPO outperforms existing methods, achieving 90% AI Win-Rate on XSum and 56% on Arena-Hard prompts after a single revision.

Classifier-based AI safety gates fail in self-improvement, even with advanced verification methods.

problem Maintaining reliable oversight of AI systems as they improve over iterations.
method Comprehensive empirical testing on neural controllers and MuJoCo benchmarks, using various classifiers and verification methods.
result Classifier-based safety gates fail in maintaining reliable oversight, even with advanced verification methods.

QuantAgent learns trading signals through self-improvement.

problem Building domain-specific knowledge for LLMs in quantitative investment.
method Two-layer loop approach: inner loop refines responses, outer loop tests and learns.
result QuantAgent approximates optimal trading behavior with provable efficiency.

SAIL-RevKL improves SAIL's convergence by regularizing the objective function.

problem Convergence of self-improving online LLM alignment algorithms.
method Proposed SAIL-RevKL, a regularized objective function to improve optimization landscape.
result Proved SAIL-RevKL satisfies the Polyak-Lojasiewicz (PL) condition with near-linear sample complexity.

SAIL improves online alignment of large language models with minimal feedback.

problem Offline RLHF methods often lead to sub-optimal performance due to fixed preference datasets.
method SAIL uses bilevel optimization and a single-level first-order method to iteratively refine model alignment.
result SAIL significantly improves alignment performance on open-sourced datasets with minimal computational overhead.

Active-GRPO improves molecular optimization by actively deciding when to imitate or self-improve.

problem Training robust and efficient molecular optimization models with large language models.
method Active-GRPO combines imitation and reinforcement learning, upgrading references and policies dynamically.
result Improves molecular optimization performance, achieving statistically significant gains.

RE enhances DL by learning model behavior, enabling iterative self-improvement.

problem Static data representations limit DL's potential for evolving models.
method RE uses multiple mappings of data through identical deep architectures, analyzing internal representations and performance signals.
result Models can gain insight from predecessors, leading to iterative self-improvement.

SIBRE boosts reinforcement learning convergence by rewarding improvement over past performance.

problem Improving the rate of convergence in reinforcement learning.
method SIBRE is a reward shaping approach that rewards improvement over the agent's own past performance.
result SIBRE converges faster and more stably to the optimal policy compared to baseline RL algorithms.

Theoretical limits on verifying self-improving systems without risking unbounded utility.

problem Formalizing and proving the limits of safety verification for self-improving systems.
method Developed dual conditions and used Holder's inequality, NP counting method, and Lipschitz bounds to establish impossibility and ceiling results.
result A classifier-based safety gate cannot simultaneously permit unbounded beneficial self-modification and bounded cumulative risk.

LaTRO optimizes latent reasoning in LLMs without external reward.

problem Training LLMs to perform complex reasoning tasks.
method Formulates reasoning as latent distribution sampling and optimizes via variational approaches.
result LLMs improve reasoning and evaluation quality through self-improvement.

RL pipeline simplifies knot diagrams, including very hard unknots.

problem Simplifying complex knot diagrams, especially very hard unknots.
method Reinforcement learning for move proposals and heuristic navigation of Reidemeister moves.
result Trained agent simplifies diagrams, including a 41#9104_1\#9_{10} link to a three-step unknotting process.

Study compares DSPy teleprompter algorithms for aligning LLM evaluations with human annotations.

problem Aligning LLM evaluation metrics with human annotations.
method Comparative analysis of five teleprompter algorithms within the DSPy framework.
result Certain teleprompters outperform others in detecting hallucinations.

Neural model accelerates SDDP for stochastic optimization.

problem Exponential complexity of SDDP limits its applicability to low-dimensional problems.
method Trainable neural model maps problem instances to a low-dimensional piecewise linear value function.
result ν-SDDP significantly reduces problem solving cost without sacrificing solution quality.

Paper addresses online alignment of large language models under uncertain preference feedback.

problem Online alignment of large language models with misspecified preference feedback.
method Formulates an oracle-robust objective as a worst-case optimization problem for log-linear policies, and develops projected stochastic composite updates.
result Shows that the robust objective admits an exact closed-form decomposition and achieves O~(ε2)\widetilde{O}(\varepsilon^{-2}) oracle complexity.

In this article, we propose the Coopetititve Soft Gating Ensemble or CSGE for general machine learning tasks and interwoven systems. The goal of machine learning is to create models that generalize well for unknown datasets. Often, however, the problems are too complex to be solved with a single model, so several model…

2018-07-03abs ↗pdf ↗

New algorithms reduce dueling bandits' regret with neural networks and efficient exploration.

problem Optimizing dueling bandits with neural networks for better performance.
method Combines shallow exploration strategies with neural networks for utility approximation, using iterative self-improvement and spectral analysis to reduce network width.
result Achieves sublinear regret of O~(dt=1Tσt2+dT)\widetilde{\mathcal{O}}(d\sqrt{\sum_{t=1}^{T} σ_t^2} + \sqrt{dT}).

Transcribing content from structural images, e.g., writing notes from music scores, is a challenging task as not only the content objects should be recognized, but the internal structure should also be preserved. Existing image recognition methods mainly work on images with simple content (e.g., text lines with charact…

2019-05-27abs ↗pdf ↗

Optimal self-distillation improves generative models' velocity risk and mode recovery.

problem Improving generative models' velocity risk and mode recovery.
method Proved optimal self-distillation for rectified flow via linear probing, derived mixing coefficient, and provided validation tuning.
result Optimal self-distillation improves velocity risk and mode recovery.

SUPE combines unlabeled data with RL to efficiently explore tasks.

problem Efficient exploration in reinforcement learning with sparse rewards.
method Extract low-level skills using VAE, pseudo-label unlabeled data, and use as off-policy data for online RL.
result SUPE outperforms prior methods across 42 long-horizon tasks.

As data-driven predictive models are increasingly used to inform decisions, it has been argued that decision makers should provide explanations that help individuals understand what would have to change for these decisions to be beneficial ones. However, there has been little discussion on the possibility that individu…

2020-02-11abs ↗pdf ↗