Proposes CLRS benchmark to evaluate algorithmic reasoning.
problem Difficulty in transferring results across publications due to targeted algorithmic data.
method Develops a comprehensive benchmark covering various algorithmic tasks.
result Demonstrates performance of algorithmic reasoning baselines on the CLRS benchmark.
Proposes CLRS-Text, a new benchmark for evaluating LM reasoning capabilities.
problem Lack of transferable benchmarks for evaluating reasoning capabilities of language models.
method Developed a textual version of the CLRS benchmark, generating diverse algorithmic tasks.
result Demonstrates a novel challenge for the LM reasoning community and validates prior work.
Graph Neural Networks align with dynamic programming, improving algorithmic reasoning.
problem Demonstrate and quantify alignment between GNNs and dynamic programming.
method Category theory and abstract algebra methods to expose intricate connection.
result Showed GNNs align with dynamic programming beyond individual algorithms.
Hybrid deep architectures with reasoning layers show promising convergence and generalization properties.
problem Understanding the theoretical foundations of hybrid deep architectures with reasoning layers.
method Analyzing the interplay between algorithm layers and neural components in deep architectures.
result Properties of algorithm layers are closely related to the approximation and generalization abilities of end-to-end models.
Neural networks have succeeded in many reasoning tasks. Empirically, these tasks require specialized network structures, e.g., Graph Neural Networks (GNNs) perform well on many such tasks, but less structured networks fail. Theoretically, there is limited understanding of why and when a network structure generalizes be…
R2-B2 optimizes game interactions with recursive reasoning.
problem Optimizing interactions between boundedly rational agents with unknown payoff functions.
method Recursive Reasoning-Based Bayesian Optimization (R2-B2) for repeated games.
result R2-B2 achieves faster asymptotic convergence to no regret than non-recursive methods.
Improved neural networks for relational reasoning by projecting high-dimensional data to low-dimensional manifolds.
problem Out-of-distribution generalization in complex relational reasoning tasks.
method Neuroscience-inspired inductive-biased module projecting high-dimensional object representations to low-dimensional manifolds.
result Significantly better out-of-distribution generalization performance on relational reasoning tasks.
Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The benchmark is designed to encourage the development of learning algorithms that are sa…
XLVINs improve deep reinforcement learning by combining self-supervised learning and neural algorithmic reasoning.
problem Limitations of Value Iteration Networks (VINs) in deep reinforcement learning.
method Combining contrastive self-supervised learning, graph representation learning, and neural algorithmic reasoning.
result XLVINs match VIN-like models on discrete, fixed MDPs and significantly outperform model-free baselines.
Semantic Web knowledge representation standards, and in particular RDF and OWL, often come endowed with a formal semantics which is considered to be of fundamental importance for the field. Reasoning, i.e., the drawing of logical inferences from knowledge expressed in such standards, is traditionally based on logical d…
Improved reasoning model by sampling from power distribution without additional training.
problem Efficiently sampling from a sharpened distribution to improve reasoning models.
method Entropy-Cut Metropolis-Hastings algorithm that identifies key decision points for resampling.
result The method consistently improves reasoning models across various datasets.
PerSense assesses personality traits from text for commonsense reasoning.
problem Estimating human personality traits from text for mental health analysis.
method Aggregated Probability Density Functions (PDF) and Machine Learning (ML) models.
result PerSense algorithms achieve comparable results to ground truth data, with high accuracy for personality assessment and commonsense prediction.
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.
RACER optimizes LLM-as-judge accuracy with dynamic reasoning selection.
problem Balancing reasoning accuracy with computational cost in LLM-as-judge settings.
method Formulates routing as a constrained distributionally robust optimization problem, accounting for distribution shift via KL-divergence uncertainty set.
result RACER achieves superior accuracy-cost trade-offs under distribution shift.
Transformers learn multi-step reasoning through gradient descent.
problem Understanding how transformers solve symbolic multi-step reasoning tasks.
method Theoretical analysis of gradient descent dynamics and multi-phase training.
result Trained one-layer transformers can solve both backward and forward reasoning tasks with generalization guarantees.
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with model-free reinforcement learning to solve a range of problems that each contain causal…
FinCARE combines financial data and AI reasoning to improve causal analysis of financial performance.
problem Correlation-based analysis fails to capture true causal relationships in financial performance.
method Hybrid framework integrating causal discovery algorithms with financial domain knowledge from SEC filings and LLM reasoning.
result KG+LLM-enhanced methods improve causal discovery across PC, GES, and NOTEARS by 36-366%.
Enhances large language models' reasoning through simpler off-policy reinforcement learning.
problem Improving large language models' ability to reason and solve problems.
method EM Policy Gradient, optimizing expected return over reasoning trajectories using Expectation-Maximization (EM) optimization.
result Achieves comparable or slightly superior performance to state-of-the-art methods on reasoning datasets, with additional cognitive behaviors.
Paper proves efficiency of MARL with transformers, addressing agent complexity.
problem Theoretical understanding of MARL with many agents and limited relational reasoning.
method Set Transformer for relational reasoning, model-free and model-based MARL algorithms.
result Provable efficiency of MARL algorithms, suboptimality gaps independent of number of agents.
A general graph-structured neural network architecture operates on graphs through two core components: (1) complex enough message functions; (2) a fixed information aggregation process. In this paper, we present the Policy Message Passing algorithm, which takes a probabilistic perspective and reformulates the whole inf…
fairadapt uses causal inference to mitigate algorithmic bias in data pre-processing.
problem Mitigating algorithmic bias in machine learning predictions.
method Causal graphical model and observed data to address counterfactual questions.
result The method can help eliminate discrimination and justify fair decisions.
Proposes a new algorithm for accurate tree-based models with guaranteed recourse actions.
problem Ensuring recourse actions for models optimized for predictive performance.
method Formulates and solves an optimization task to ensure reasonable actions for as many instances as possible, using adversarial training techniques.
result Successfully provided reasonable actions to more instances than baselines without significantly degrading accuracy and computational efficiency.
Large language models can't efficiently reason conditionally in a distribution-free setting.
problem Impossibility of conditional PAC-efficient reasoning in large language models.
method Proof of impossibility in a distribution-free setting for non-atomic input spaces.
result Any algorithm achieving conditional PAC efficiency must defer to the expert model with high probability.
Calibrated PRMs improve inference efficiency for LLMs by dynamically adjusting compute budgets.
problem Poor calibration of PRMs leads to overestimation of success probabilities in partial reasoning steps.
method Quantile regression for calibration, instance-adaptive scaling (IAS) framework.
result Calibrated PRMs reduce inference costs while maintaining accuracy, especially on confident problems.
Researchers analyze and improve latent space in NAR models.
problem Latent space resolution and range issues in NAR models.
method Detailed analysis of GNN latent space structure, proposing and testing solutions.
result Improvements in majority of algorithms on CLRS-30 benchmark.
Paper closes neural-symbolic learning loop with grammar model and back-search algorithm.
problem Slow convergence in neural-symbolic learning due to error propagation issues.
method Introduces grammar model as symbolic prior and back-search algorithm for efficient error propagation.
result Significantly outperforms RL methods in performance, converging speed, and data efficiency.
Bayesian network classifiers are used in many fields, and one common class of classifiers are naive Bayes classifiers. In this paper, we introduce an approach for reasoning about Bayesian network classifiers in which we explicitly convert them into Ordered Decision Diagrams (ODDs), which are then used to reason about t…
MIM-Reasoner learns seed users for maximizing influence in multiplex networks.
problem Maximizing influence in multiplex networks with multiple layers of social interactions.
method Combining reinforcement learning with probabilistic graphical models.
result Established a theoretical guarantee for MIM-Reasoner's performance.
Paper improves robustness certification by integrating ML and logical reasoning.
problem Limited robustness certification under perturbation radius.
method Integrates statistical ML models with logical reasoning using Markov logic networks.
result First certified robustness bound for MLN derived and experimentally validated.
Transformers solve parity problems efficiently with step-by-step reasoning.
problem Training transformers to solve complex, recursive problems like parity.
method Training a one-layer transformer to solve k-parity, incorporating intermediate parities into the loss function, and using teacher forcing or augmented data. result Transformers can learn parity in one gradient update with intermediate supervision or self-consistency checks.
The paper proposes a framework to reason about object dynamics for faster reinforcement learning.
problem Current reinforcement learning approaches lack prior knowledge about the environment, limiting efficiency.
method Integrates object dynamics and behavior into reinforcement learning to improve efficiency.
result Demonstrates the need for reasoning about object behavior and dynamics, leading to faster learning.
FLOP algorithm speeds up causal structure learning for linear models.
problem Efficiently learning causal structures from discrete data.
method FLOP algorithm combines fast parent selection and iterative score updates.
result FLOP finds highly accurate causal structures with near-perfect recovery.
Neural networks mimic algorithms to solve complex problems.
problem Current machine learning methods struggle with generalisation and efficiency.
method Representing algorithms in a continuous space and adapting them to real-world problems.
result Neural networks can execute classical algorithms more efficiently.
Method guarantees coherent factuality for language model outputs in reasoning tasks.
problem Ensuring correctness of language model outputs in reasoning tasks.
method Developed a conformal-prediction-based method applied to subgraphs within a deducibility graph.
result Achieved coherent factuality across target coverage levels, 90% on stricter definition.
We review three algorithms for Latent Dirichlet Allocation (LDA). Two of them are variational inference algorithms: Variational Bayesian inference and Online Variational Bayesian inference and one is Markov Chain Monte Carlo (MCMC) algorithm -- Collapsed Gibbs sampling. We compare their time complexity and performance.…
New method explains anomalies in multivariate time series data.
problem Understanding and explaining anomalies in multivariate time series data.
method Counterfactual reasoning applied to MDI-detected anomalous intervals.
result Our method accurately identifies and explains anomalies in various extreme events.
TRR detects stock portfolio crashes by simulating human reasoning.
problem Detecting stock portfolio crashes with limited historical data.
method Temporal Relational Reasoning (TRR) framework.
result TRR outperforms state-of-the-art techniques in detecting stock portfolio crashes.
BASIS improves LLM reasoning by sharing batchwise rollout info, reducing MSE by 69%.
problem Improving large language model reasoning with limited rollouts and batch information.
method BASIS samples only one rollout per prompt but uses batch information to improve value function estimation.
result BASIS reduces MSE in value function estimation by 69% compared to REINFORCE++.
SFPO optimizes LLM reasoning by repositioning before updating, improving stability and efficiency.
problem Noisy gradients from low-quality rollouts cause instability and inefficient exploration in on-policy RL algorithms.
method Decomposes each step into three stages: a short fast trajectory, repositioning, and slow correction, preserving the objective and rollout process unchanged.
result SFPO consistently improves stability, reduces rollouts, and accelerates convergence, outperforming GRPO on math reasoning benchmarks.
Curriculum learning improves model training efficiency and performance.
problem Expensive training of reasoning models using human or synthetic data.
method Autocurriculum, where models use their own performance to decide training problems.
result Autocurriculum reduces training costs and improves model performance.
ENN neural network learns logical syllogisms using Euler diagrams.
problem Traditional neural networks struggle with logical reasoning, especially syllogisms.
method ENN represents logical relations as Euler diagrams, optimizing syllogism structures with a novel back-propagation algorithm.
result ENN can precisely represent and reason with all 24 syllogism structures.
While the machine learning literature dedicated to fully automated reasoning algorithms is abundant, the number of methods enabling the inference process on the basis of previously defined knowledge structures is scanter. Fuzzy Cognitive Maps (FCMs) are neural networks that can be exploited towards this goal because of…
New methods for explaining Random Forest predictions using case-based reasoning.
problem Lack of explainability for black-box machine learning models like Random Forests.
method Extracting distance metric from Random Forests to identify prototypes, critics, counter-factuals, and semi-factuals.
result Identified special points from training datasets to explain Random Forest predictions.
A new fast algorithm solves SLOPE optimization problem.
problem Inefficient algorithms for SLOPE optimization in high dimensions.
method Combines proximal gradient descent and proximal coordinate descent steps.
result Our method outperforms competing algorithms in benchmarks.
Humans are capable of attributing latent mental contents such as beliefs or intentions to others. The social skill is critical in daily life for reasoning about the potential consequences of others' behaviors so as to plan ahead. It is known that humans use such reasoning ability recursively by considering what others …
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.
Formalizes weak and strong verification for LLMs, controlling errors without assumptions.
problem Balancing cost and reliability in reasoning with LLMs.
method Formalizes weak-strong verification policies, introduces metrics, develops online algorithm.
result Optimal policies admit a two-threshold structure, and calibration and sharpness govern value of weak verifiers.
While implicit feedback (e.g., clicks, dwell times, etc.) is an abundant and attractive source of data for learning to rank, it can produce unfair ranking policies for both exogenous and endogenous reasons. Exogenous reasons typically manifest themselves as biases in the training data, which then get reflected in the l…