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.

169,051 papers · 148 categories

Trend · papers per month

12243648 · Jun 202019922001200920182026
48 results for reflective thinking

Automatic detection of reflective thinking in math problem solving using body movement data.

problem Detecting reflective thinking in children's mathematical problem solving.
method WeDraw-1 Movement Dataset, Long Short-Term Memory neural networks, end-to-end detection.
result Average F1 scores of 0.73 for automatic detection and 0.79 for end-to-end detection of reflective thinking.

Human inertial thinking schemes can be formed through learning, which are then applied to quickly solve similar problems later. However, when problems are significantly different, inertial thinking generally presents the solutions that are definitely imperfect. In such cases, people will apply creative thinking, such a…

2018-03-01abs ↗pdf ↗

CausalGame benchmarks LLM agents' causal thinking in games.

problem Evaluating causal thinking in AI Scientists with LLMs.
method Interactive games with 14 scenarios incorporating selection bias, measurement error, and hidden confounders.
result None of the 30 LLM agents demonstrated reliable causal thinking, with the best model achieving only 68.0% survival.

This paper uses counterfactual thinking to improve multi-agent reinforcement learning.

problem Improving decision-making in multi-agent environments.
method Proposes a deep reinforcement learning model with counterfactual thinking to generate and evaluate multiple actions.
result Counterfactual thinking enhances agents' performance in multi-agent environments, leading to higher rewards and fair competition.

Look-ahead reasoning helps predict strategic user behavior on learning platforms.

problem Optimization criteria on learning platforms do not reflect users' priorities.
method Formalized level-k thinking and contrasted collective and selfish behavior.
result Coordination benefits users but does not offer higher-level reasoning advantages in the long run.

A new reinforcement learning method for robots thinking and moving simultaneously.

problem Concurrent control in robotic systems where actions must be decided while the system is still evolving.
method Continuous-time Bellman equations, discretization aware of system delays, and architectural extension to deep reinforcement learning.
result The method successfully handles tasks requiring simultaneous decision-making and action execution.

Model learns brevity by exposing to easy problems, improving efficiency without explicit length penalties.

problem Excessive verbosity in step-by-step reasoning models trained with RLVR.
method Retaining and up-weighting moderately easy problems as implicit length regularizers.
result Model generates solutions that are, on average, nearly twice as short without explicit length penalties.

Thinking LLMs struggle with stock prediction, especially as data complexity increases.

problem Evaluating the performance of 'thinking' LLMs in stock prediction, especially under varying levels of cross-sectional complexity.
method Rolling 48m/1m walk-forward evaluation, comparing direct LLMs, TLLMs, and classical learners on cross-sectional ranking loss, MSE, and backtests with transaction costs.
result TLLMs' ranking quality deteriorates as cross-sectional complexity grows, while direct LLMs remain stable.

DGP learns speech recognition by modeling complex relationships between utterances.

problem Modeling complex relationships in speech recognition without relational data.
method Bayesian nonparametric deep learning method (DGP) that generates infinite probabilistic graphs.
result DGP successfully infers relationships among utterances without relational data during training.

Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans …

2016-04-01abs ↗pdf ↗

Simple model outperforms neural networks on language understanding tasks.

problem Neural networks struggle with creating novel expressions from familiar ones.
method Attention-inspired modification of a baseline model, focusing on sequential thinking and acting.
result Simple model achieves good performance on gSCAN tasks, validating the benchmark.

The success of deep neural networks has inspired many to wonder whether other learners could benefit from deep, layered architectures. We present a general framework called forward thinking for deep learning that generalizes the architectural flexibility and sophistication of deep neural networks while also allowing fo…

2017-05-20abs ↗pdf ↗

TSDS framework reduces edge LLM agent compute by 43%-73% while maintaining safety and reliability.

problem Managing reasoning budget and uncertainty in edge LLM agents.
method Integrates a lightweight convergence probe and a perplexity-based deferral rule calibrated via multi-objective LTT.
result Reduces per-episode thinking compute by 43%-73% over deferral-only baselines.

Breiman's paper sparked debate on the future of statistics and machine learning.

problem The tension between traditional statistical modeling and model-free machine learning approaches.
method Discussion of the implications of machine learning's success and the need for new inferential approaches.
result The importance of understanding 'why' and 'if' questions in machine learning is now recognized.

Research suggests using deep learning for better recommendation systems.

problem Recommender systems rely on proxies for A/B testing, leading to random success.
method Advocates for using deep learning to improve recommendation performance.
result Deep learning can potentially optimize reward in recommendation systems.

In this paper we study n-composition series of affine manifolds. One composition series are classified using gerbe theory. It is natural to think that n-composition series must be classified using n-gerbe theory. In the last section of this, we propose a notion of abelian n-gerbe theory

2001-05-24abs ↗pdf ↗

The paper converts metric bounds to distance function Hölder bounds and proves compactness theorems.

problem Proving geometric stability results with scalar curvature bounds.
method Transforming LpL^p bounds to Hölder bounds for distance functions.
result Compactness theorems and convergence guarantees for Riemannian manifolds.

A discrete subgroup of the group of isometries of the hyperbolic space is called reflective if up to a finite index it is generated by reflections in hyperplanes. The main result of this paper is a complete classification of the reflective (and quasi-reflective) subgroups among the Bianchi groups and their extensions.

2012-10-09abs ↗pdf ↗

Survey explores interactions between four conformal dynamics branches.

problem Understanding complex dynamics through different mathematical concepts.
method Examples and general results with technical tools.
result Dynamical relations between Schwarz reflection parameter spaces and anti-rational maps/ reflection groups.

We argue that the present crisis and stalling economy continuing since 2007 are rooted in the delusionary belief in policies based on a "perpetual money machine" type of thinking. We document strong evidence that, since the early 1980s, consumption has been increasingly funded by smaller savings, booming financial prof…

2012-12-12abs ↗pdf ↗

DRNets combine deep learning and reasoning for complex tasks.

problem Solving complex tasks, especially in scientific discovery, with limited supervision.
method DRNets integrate logic and neural network optimization to encode structured latent spaces constrained by prior knowledge.
result DRNets outperform state-of-the-art models in scientific discovery tasks, recovering more precise crystal structures.

Minimal surfaces in 3-sphere created by reflections from polygons, with new examples based on pentagons.

problem Constructing minimal surfaces in 3-sphere using reflections.
method Minimal nn-gon solves free boundary problem; curvature lines combinatorics investigated.
result New examples of minimal reflection surfaces based on pentagons.

There is no doubt that both the special and general theories of relativity capture the imagination. The anti-intuitive properties of the special theory of relativity and its deep philosophical implications, the bizzare and dazzling predictions of the general theory of relativity: the curvature of spacetime, the exotic …

2011-12-04abs ↗pdf ↗

We prove new results on existence of solutions for the prescribed gaussian curvature problem on the euclidean sphere S^2. Those results are achieved by relating this problem with the holomorphic triples theory on Riemann surfaces. We think this approach might be applied to study some other semi-linear elliptic equation…

2015-03-19abs ↗pdf ↗

The paper classifies a specific type of hyperbolic lattices using geometric properties.

problem Classifying (1,2)(1{,}2)-reflective anisotropic hyperbolic lattices of rank 44.
method Using geometric properties of the fundamental polyhedron of a cocompact reflection group in three-dimensional Lobachevsky space.
result A classification of (1,2)(1{,}2)-reflective anisotropic hyperbolic lattices of rank 44.