Related papers: Automating Agential Reasoning: Proof-Calculi and S…
Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We introduce Materials Agents for Simulation and Theory in…
Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world…
Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample…
A key challenge in automated formal reasoning is the intractable search space, which grows exponentially with the depth of the proof. This branching is caused by the large number of candidate proof tactics which can be applied to a given…
Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly,…
We present a systematic empirical study of prompt engineering for formal mathematical reasoning in the context of the SAIR Equational Theories Stage 1 competition. The task requires deciding whether one equational law implies another over…
Current Natural Language Inference (NLI) models achieve impressive results, sometimes outperforming humans when evaluating on in-distribution test sets. However, as these models are known to learn from annotation artefacts and dataset…
We introduce SLR, an end-to-end framework for systematic evaluation and training of Large Language Models (LLMs) via Scalable Logical Reasoning. Given a user's task specification, SLR automatically synthesizes (i) an instruction prompt for…
Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and problem-solving across various domains. However, their ability to perform complex, multi-step reasoning task-essential…
In this paper we present analytic tableau proof systems for various justification logics. We show that the tableau systems are sound and complete with respect to Mkrtychev models. In order to prove the completeness of the tableaux, we give…
The present paper provides an analysis of the existing proof systems for dynamic epistemic logic from the viewpoint of proof-theoretic semantics. Dynamic epistemic logic is one of the best known members of a family of logical systems which…
Automated theorem proving is fundamental to formal methods, and the recent trend is to integrate large language models (LLMs) and proof assistants to form effective proof agents. While existing proof agents show promising performance, they…
We give a linear nested sequent calculus for the basic normal tense logic Kt. We show that the calculus enables backwards proof-search, counter-model construction and syntactic cut-elimination. Linear nested sequents thus provide the…
Large Language Models (LLMs) equipped with external tools have demonstrated enhanced performance on complex reasoning tasks. The widespread adoption of this tool-augmented reasoning is hindered by the scarcity of domain-specific tools. For…
This paper presents a comprehensive framework for modeling and verifying multi-agent systems. The paper introduce an Epistemic Process Calculus for multi-agent systems, which formalizes the syntax and semantics to capture the essential…
Multi-agent LLM systems increasingly tackle complex reasoning, yet their interaction patterns remain limited to voting, unstructured debate, or pipeline orchestration. None model deliberation: a phased process where differentiated…
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks, sparking growing interest in their application to preference reasoning in recommendation systems. Existing methods typically…
Large language models (LLMs) face challenges in solving complex mathematical problems that require comprehensive capacities to parse the statements, associate domain knowledge, perform compound logical reasoning, and integrate the…
The current technology landscape lacks a foundational AI model for solving process engineering calculations. In this work, we introduce a novel autonomous agent framework leveraging Retrieval-Augmented Instruction-Tuning (RAIT) to enhance…
Large Language Models (LLMs) often produce answers with a single chain-of-thought, which restricts their ability to explore reasoning paths or self-correct flawed outputs in complex tasks. In this paper, we introduce MALT (Multi-Agent LLM…