This work investigates how multi-round reasoning improves LLM performance.
problem Improving problem-solving abilities in complex tasks with LLMs.
method Investigates approximation, learnability, and generalization properties of multi-round auto-regressive models.
result Transformers with finite context windows are universal approximators for Turing-computable functions and can approximate any Turing-computable sequence-to-sequence function through multi-round reasoning.
Improved self-distillation reduces label noise and enhances model accuracy.
problem Label noise in multi-class classification.
method Label averaging and refined partial labels.
result Single-round self-distillation achieves comparable performance to multi-round distillation.
We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This targeting behavior is learnt solely from downstream task-specific reward withou…
Reciprocating interactions represent a central feature of all human exchanges. They have been the target of various recent experiments, with healthy participants and psychiatric populations engaging as dyads in multi-round exchanges such as a repeated trust task. Behaviour in such exchanges involves complexities relate…
Develops methods to learn centre groupings from summary statistics in multi-centre studies.
problem Violation of homogeneity of parameters across centres in multi-centre studies.
method Clusters-of-Centres (CoC) algorithm that merges centres based on multivariate Cochran-type tests.
result Golden-partition recovery as the number of rounds grows with sample size.
Mechanism designs for unknown agent values in stochastic bandit settings.
problem Designing truthful mechanisms for maximizing social welfare in settings with unknown agent values and stochastic feedback.
method Developed a VCG-like mechanism with regret bounds for multi-round allocations, balancing agent and seller welfare.
result Achieved an $Ω(T^{ rac{2}{3}})$ lower bound for the maximum of welfare, agent utilities, and mechanism utility after T rounds. We introduce the community exploration problem that has many real-world applications such as online advertising. In the problem, an explorer allocates limited budget to explore communities so as to maximize the number of members he could meet. We provide a systematic study of the community exploration problem, from off…
SAFLe solves federated learning's trade-off between non-linearity and scalability.
problem Federated Learning's high communication overhead and performance collapse on non-IID data.
method SAFLe introduces a structured head of bucketed features and sparse, grouped embeddings, mathematically equivalent to a high-dimensional linear regression.
result SAFLe achieves a new state-of-the-art in analytic FL, outperforming linear AFL and multi-round DeepAFL.
This paper analyzes Local SGD for federated learning, achieving both statistical and communication efficiency.
problem Statistical estimation and inference in federated learning with decentralized data.
method Local SGD, a multi-round estimation procedure using intermittent communication.
result Local SGD achieves both statistical efficiency and communication efficiency.
Optimizes financial decisions with illiquid assets using Kelly criterion.
problem Determining optimal betting strategies in games with external capital constraints.
method Dynamic programming and WKB approximation for multi-round games; Kelly criterion for single-round games.
result Rational players adjust their risk-taking based on the proportion of their capital locked away.
Proposes Fusion Recurrent Neural Network for sequence data.
problem Improving sequence learning for practical applications.
method Fusion module and Transport module for sequence data.
result Fusion RNN performs comparably to state-of-the-art RNNs.
New framework assesses LLM security risks in BFSI.
problem Lack of domain-specific security evaluation for LLMs in BFSI.
method Risk-aware evaluation framework combining taxonomy, automated red-teaming, and ensemble judging.
result Higher decoding stochasticity and adaptive interaction lead to more severe disclosures.
The growing size of modern data brings many new challenges to existing statistical inference methodologies and theories, and calls for the development of distributed inferential approaches. This paper studies distributed inference for linear support vector machine (SVM) for the binary classification task. Despite a vas…
We study the tradeoff between the statistical error and communication cost of distributed statistical estimation problems in high dimensions. In the distributed sparse Gaussian mean estimation problem, each of the m machines receives n data points from a d-dimensional Gaussian distribution with unknown mean θ w…
Game theory models incentivizes honesty in collaborative learning among competitors.
problem Incentivizing honest updates among competitors in collaborative learning schemes.
method Formulated a game to model interactions, studied two learning tasks, proposed mechanisms to incentivize honest communication.
result Rational clients are incentivized to manipulate their updates, preventing learning; proposed mechanisms ensure comparable learning quality to full cooperation.
Paper develops a distributed debiased estimator for sparse statistical inference.
problem High computational costs in debiased estimator construction for high-dimensional models.
method Develops a multi-round distributed debiased estimator using both labeled and unlabelled data.
result Unlabeled data improves statistical rate of each iteration in distributed setup.
The paper develops efficient estimators for semi-parametric binary models in distributed computing.
problem Estimation and inference challenges in large-scale data under non-smooth objective functions.
method Proposes one-shot and multi-round divide-and-conquer estimators with adaptive kernel smoothing to relax constraints and achieve superlinear optimization error.
result Establishes quadratic convergence up to optimal statistical error rate and handles dataset heterogeneity and high-dimensional sparse parameters.
QuantaAlpha uses evolutionary algorithms to mine financial alpha robustly across market distributions.
problem Challenges in alpha mining due to market noise and regime shifts.
method Evolutionary framework treating each mining run as a trajectory, mutation, crossover, targeted revision, and reuse of effective patterns.
result Consistent gains over strong baselines and prior systems, achieving high IC and ARR.
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.
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.
A framework isolates VQA reasoning from perception for better model evaluation.
problem Improper separation of visual perception and reasoning in VQA models.
method Introducing a framework and a top-down calibration technique to decouple reasoning from perception.
result Improved evaluation of VQA models by separating reasoning from perception.
This paper studies distributed estimation and inference for a general statistical problem with a convex loss that could be non-differentiable. For the purpose of efficient computation, we restrict ourselves to stochastic first-order optimization, which enjoys low per-iteration complexity. To motivate the proposed metho…
A new method for math reasoning that allows for iterative correction.
problem Standard reasoning models commit to each token and cannot recover from early errors.
method Generative framework with latent thought vectors for iterative self-correction.
result 30 rethinking iterations surpass baselines with 15 times more parameters.
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies have focused on relation types unseen in the original KG, given only one or a few instances for training. To bridge this gap, we propose Co…
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.
Transformers with CoT don't enhance reasoning power across all tasks.
problem Does CoT enhance the reasoning power of transformers?
method Examined the memorization capabilities of fixed-precision transformers with and without CoT.
result Transformers with CoT cannot memorize all reasoning tasks, leading to a negative answer.
Early stopping methods reduce unnecessary reasoning steps in LLMs by monitoring uncertainty signals.
problem LLMs sometimes generate unnecessary reasoning steps, especially under uncertainty.
method Statistically principled early stopping methods that monitor uncertainty signals during generation.
result Uncertainty-aware early stopping improves efficiency and reliability in LLM reasoning, especially in math reasoning.
Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Stand…
FinTradeBench benchmarks LLMs for financial reasoning combining company fundamentals and market signals.
problem Challenges in evaluating financial reasoning models for LLMs.
method Developed a benchmark integrating company fundamentals and trading signals, using a calibration-then-scaling framework.
result Clear performance gap between LLMs, retrieval improves reasoning over textual fundamentals but not trading signals.
Hybrid framework injects TSLM insights into GRLM for robust time-series reasoning.
problem Lack of domain-specific knowledge in large language models for time-series reasoning.
method Hybrid knowledge-injection framework combining RLVR for efficient knowledge transfer.
result Consistently outperforms existing models by 7.9%-26.1% on multivariate time-series benchmarks.
Neural Logic Reasoning integrates deep learning and symbolic logic for better prediction tasks.
problem Lack of cognitive reasoning in deep neural networks limits their ability to solve complex prediction tasks.
method Proposes Logic-Integrated Neural Network (LINN) that learns logical operations and conducts propositional logical reasoning.
result LINN significantly outperforms state-of-the-art recommendation models in Top-K recommendation.
Forward-prediction models enhance physical reasoning, but only for specific tasks.
problem Improving physical reasoning in complex tasks involving many objects.
method Incorporated forward-prediction models into simple physical-reasoning agents and evaluated their performance on the PHYRE benchmark.
result Forward-prediction models improve physical-reasoning performance, especially on complex tasks, but generalization to new task templates is challenging.
Without relevant human priors, neural networks may learn uninterpretable features. We propose Dynamics of Attention for Focus Transition (DAFT) as a human prior for machine reasoning. DAFT is a novel method that regularizes attention-based reasoning by modelling it as a continuous dynamical system using neural ordinary…
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.
VTA combines verbal and latent reasoning for accurate stock time-series forecasts.
problem Challenges in combining textual analysis with time-series data for financial forecasting.
method Converts stock price data into textual annotations, optimizes reasoning trace using inverse MSE, conditions time-series model outputs on reasoning attributes.
result VTA achieves state-of-the-art forecasting accuracy and interpretable reasoning traces.
Fractured Sampling improves LLM reasoning efficiency by truncating CoT trajectories.
problem Efficiently scaling reasoning in large language models with limited tokens.
method Integrating truncated Chain-of-Thought (CoT) with Fractured Sampling across multiple dimensions.
result Fractured Sampling achieves superior accuracy-cost trade-offs compared to full CoT.
SRN improves set representations for relational reasoning.
problem Set permutational invariance limitations in existing approaches.
method Proposed a Set Refiner Network (SRN) to respect set invariance.
result Substantial gains in prediction performance and robustness on relational reasoning tasks.
Few-shot visual reasoning model learns analogical relationships from small data.
problem Training deep models on few samples for visual reasoning tasks.
method Meta-analogical contrastive learning to enforce structural similarity between training and test samples.
result Method outperforms state-of-the-art on RAVEN dataset with scarce training data.
Study reveals how depth of reasoning affects generalization in models.
problem Understanding scaling behavior of generalization with CoT depth.
method Theoretical model of CoT in linear regression using random matrix theory.
result Sharp phase transition between exponential and polynomial improvement, saturation, and overthinking.
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.
Self-supervised skip-tree training improves mathematical reasoning in language models.
problem Improving logical reasoning in language models for formal mathematics.
method Self-supervised language modeling on mathematical formulas, skip-tree task.
result Models trained on skip-tree task outperform standard models in mathematical reasoning tasks.
Theoretical work shows integrating coherent reasoning improves LLM performance and error correction.
problem Improving reasoning and error correction in large language models (LLMs) with few-shot prompting.
method Theoretical analysis and sensitivity experiments on transformer behavior with coherent reasoning and corrupted demonstrations.
result The transformer gains better error correction ability and more accurate predictions when coherent reasoning is integrated.
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.
MXGNet tackles visual reasoning tasks using graph neural networks.
problem Abstract reasoning, especially in the visual domain, is challenging for AI.
method Combines object-level representations, graph neural networks, and multiplex graphs.
result Achieves state-of-the-art accuracy on Euler Diagram Syllogisms and outperforms state-of-the-art models on RPM datasets.
This study explains RL training dynamics in LLMs, focusing on token-level optimization and reasoning pattern reshaping.
problem Understanding the training dynamics of RL in LLMs to improve their reasoning capabilities.
method Empirical analysis and theoretical modeling of RL training process, focusing on reasoning patterns and token optimization.
result RL primarily optimizes a sparse subset of critical tokens, reshaping reasoning pattern distributions and affecting model performance.
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.
The paper studies how search and distillation improve reasoning in large language models.
problem Improving reasoning capabilities of large language models.
method Viewing chain-of-thought generation as a metastable Markov process, proving benefits of search and distillation.
result Search protocol rewards sparse edges, reducing the expected number of steps to reach different clusters.
New method finds smaller networks with similar performance to large models in fewer epochs.
problem Training large neural networks is computationally expensive and energy-intensive.
method Use PCA to identify a basis of hidden layer activations and reduce network parameters.
result Principal Component Networks (PCNs) can train faster and use less energy than overparameterized models without accuracy loss.