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.

168,657 papers · 148 categories

Trend · papers per month

52103155206 · Jun 202019922001200920172026
48 results for agentic theorem provers

Study improves understanding of why agentic theorem provers succeed.

problem Understanding which components of agentic theorem provers improve proof success.
method Statistical provability theory and finite-horizon reachability MDP model.
result Bounds provability gap and explains components' effectiveness.

We consider the task of automated theorem proving, a key AI task. Deep learning has shown promise for training theorem provers, but there are limited human-written theorems and proofs available for supervised learning. To address this limitation, we propose to learn a neural generator that automatically synthesizes the…

2020-02-17abs ↗pdf ↗

In this paper, we demonstrate how to do automated theorem proving in the presence of a large knowledge base of potential premises without learning from human proofs. We suggest an exploration mechanism that mixes in additional premises selected by a tf-idf (term frequency-inverse document frequency) based lookup in a d…

2019-05-25abs ↗pdf ↗

LeanDojo removes barriers to theorem proving with open-source tools and data.

problem Difficulty in reproducing and building on existing theorem proving methods.
method Introduces LeanDojo, an open-source Lean playground with toolkits, data, models, and benchmarks.
result ReProver, an LLM-based prover augmented with retrieval, outperforms non-retrieval baselines and GPT-4.

Scalable verifier for recurrent neural networks using polyhedral abstractions.

problem Certifying the correctness of recurrent neural networks.
method Combining sampling, optimization, and Fermat's theorem for polyhedral abstractions; gradient descent for refinement.
result Successfully verified challenging recurrent models in various domains.

Formalizes vNM utility theorem using Lean 4, proving existence and uniqueness.

problem Formalizing and proving the von Neumann-Morgenstern utility theorem.
method Implement classical axioms in Lean 4, formalizing preference relations over lotteries.
result Machine-verified proofs of existence and uniqueness of utility representations.

Benchmark for math reasoning models from human proofs.

problem Measuring and accelerating machine learning models in high-level mathematical reasoning.
method Built a non-synthetic dataset from theorem prover proofs, defined a task for model to fill in missing propositions, used hierarchical transformer to improve performance.
result Neural models can capture non-trivial mathematical reasoning, hierarchical transformer outperforms baseline.

In this article, we introduce rack invariants of oriented Legendrian knots in the 3-dimensional Euclidean space endowed with the standard contact structure, which we call Legendrian racks. These invariants form a generalization of the quandle invariants of knots. These rack invariants do not result in a complete invari…

2017-06-23abs ↗pdf ↗

Paper formalizes multi-dimensional FSD using geometric methods.

problem Complex measure theory and calculus barriers to formalization in proof assistants.
method Geometric framework for first-order stochastic dominance in N dimensions.
result Geometric approach bypasses complex integration theory for direct comparison of survival probabilities.

Lean Copilot uses LLMs to assist theorem proving in Lean, improving efficiency and automation.

problem Challenges in using existing neural theorem provers to prove novel theorems autonomously.
method Introduces Lean Copilot, a framework for integrating LLMs into Lean's theorem proving process.
result Lean Copilot automates 74.2% of proof steps on average, significantly improving over existing methods.

In this paper, we introduce a system called GamePad that can be used to explore the application of machine learning methods to theorem proving in the Coq proof assistant. Interactive theorem provers such as Coq enable users to construct machine-checkable proofs in a step-by-step manner. Hence, they provide an opportuni…

2018-06-02abs ↗pdf ↗

This paper presents the first use of graph neural networks (GNNs) for higher-order proof search and demonstrates that GNNs can improve upon state-of-the-art results in this domain. Interactive, higher-order theorem provers allow for the formalization of most mathematical theories and have been shown to pose a significa…

2019-05-24abs ↗pdf ↗

We explore the application of automated reasoning techniques to unknot detection, a classical problem of computational topology. We adopt a two-pronged experimental approach, using a theorem prover to try to establish a positive result (i.e. that a knot is the unknot), whilst simultaneously using a model finder to try …

2014-05-16abs ↗pdf ↗

We introduce a formal framework for analyzing trades in financial markets. An exchange is where multiple buyers and sellers participate to trade. These days, all big exchanges use computer algorithms that implement double sided auctions to match buy and sell requests and these algorithms must abide by certain regulator…

2019-07-18abs ↗pdf ↗

Neural symbolic processing aims to combine the generalization of logical learning approaches and the performance of neural networks. The Neural Theorem Proving (NTP) model by Rocktaschel et al (2017) learns embeddings for concepts and performs logical unification. While NTP is promising and effective in predicting fact…

2019-06-17abs ↗pdf ↗

Paper formalizes Simon's satisficing through FFSD, proving its equivalence to expected utility theory.

problem Formalizing Herbert Simon's bounded rationality concept in economic decision-making.
method Developed FFSD framework using Lean 4 theorem prover, proving equivalence to expected utility theory.
result Equivalence theorem linking FFSD to expected utility maximization for approximate indicator functions.

INT benchmark tests theorem proving agents' ability to generalize to unseen theorems.

problem Evaluating theorem proving agents' ability to generalize to unseen theorems.
method INT benchmark based on a theorem generation and proof procedure with adjustable knobs for measuring 6 types of generalization.
result MCTS can help agents prove new theorems.

The paper extends collective arbitrage concepts to multi-agent markets with cooperation.

problem Understanding collective market completeness and pricing in multi-agent systems.
method Develops new techniques and theorems to establish collective pricing-hedging duality and collective replication.
result Established a Second Fundamental Theorem of Asset Pricing in cooperative multi-agent settings.

This research simplifies verification of machine learning systems using reparameterization.

problem Reduce or eliminate serious bugs in machine learning systems.
method Use proof assistants to construct machine-checked proofs of correctness, leveraging reparameterization to handle probabilistic claims.
result Demonstrates broad applicability of reparameterization to verify different types of machine learning systems.

UD-SGD analysis shows efficient sampling by a few agents can outperform others.

problem Analyzing convergence speed and sampling strategies in UD-SGD.
method Asymptotic analysis of UD-SGD with various communication patterns and sampling strategies.
result Efficient sampling by a few agents can lead to better overall convergence.

New theorems show agents need specific internal structures to perform well under uncertainty.

problem How do agents need to be structured to perform well under uncertainty?
method Proved selection theorems showing strong task performance forces specific internal structures.
result Strong task performance forces world models, belief-like memory, and persistent regime-tracking variables.

Generalizes risk sharing models to a continuum of agents.

problem Risk sharing among a large number of heterogeneous agents.
method Modeling agents as points in a measure space, using risk measures on a probability space, and deriving dual representations.
result Explicit formulas for specific risk measures (entropic and expected shortfall) and applications to Pareto efficiency.

Study explores algorithmic collusion in repeated games using various learning dynamics.

problem Understanding algorithmic collusion in repeated games with different learning dynamics.
method Examines QQ-learning, gradient learning, and other dynamics in a general repeated game setting.
result Characterizes the set of payoff vectors achievable by these dynamics, revealing possibilities for collusion.

Examines optimal risk sharing with realistic risk attitudes, finding risk seeking in certain subdomains.

problem Optimal risk sharing with empirically realistic risk attitudes.
method Allows for risk-seeking agents, generalizes expected utility, and uses counter-monotonic improvement theorem.
result First empirical results on optimal risk sharing with realistic risk attitudes.

Bayesian network approach for efficient cooperative MARL.

problem Leveraging inter-agent coupling information for scalable MARL algorithms.
method Modeling cooperative MARL via Bayesian networks, identifying value dependency sets, proposing P-DTDE paradigm.
result P-DTDE policy gradient estimator has lower total variance than CTDE.

We develop original models to study interacting agents in financial markets and in social networks. Within these models randomness is vital as a form of shock or news that decays with time. Agents learn from their observations and learning ability to interpret news or private information in time-varying networks. Under…

2019-04-17abs ↗pdf ↗

DSAC improves cooperative MARL with general utilities, converging faster than existing methods.

problem Improving cooperation in multi-agent reinforcement learning with nonlinear utilities.
method Decentralized Shadow Reward Actor-Critic (DSAC) that estimates local occupancy measures and derivatives.
result DSAC converges to ε-stationarity in O(1/ε^2.5) steps with high probability, finding globally optimal policies.

The study proves necessary conditions for robust decision-making in uncertain environments.

problem Conditions for robust decision-making in uncertain environments.
method Quantitative selection theorems and binary betting decisions.
result World models, belief-like memory, and persistent variables are necessary for strong task performance.

The paper gives picture of enrichment to economic and financial system analysis using agent-based models as a form of advanced study for financial economic data post-statistical-data analysis and micro-simulation analysis. Theoretical exploration is carried out by using comparisons of some usual financial economy syste…

2004-03-21abs ↗pdf ↗

The paper addresses how to complete incomplete risk markets by iteratively enhancing welfare.

problem How to complete incomplete risk markets to enhance welfare.
method Iterative mechanism to complete the market while monotonically enhancing welfare.
result Iterative completion of incomplete risk markets can enhance welfare.

In this communication, some economic models given by functional mappings are addressed. These are models for random markets where agents trade by pairs and exchange their money in a random and conservative way. They display the exponential wealth distribution as asymptotic equilibrium, independently of the effectivenes…

2013-07-08abs ↗pdf ↗