Related papers: A Model Checker for Natural Strategic Ability
Large language models (LLMs) such as ChatGPT have recently demonstrated significant potential in mathematical abilities, providing valuable reasoning paradigm consistent with human natural language. However, LLMs currently have difficulty…
In this paper, we consider the problem of long tail scenario modeling with budget limitation, i.e., insufficient human resources for model training stage and limited time and computing resources for model inference stage. This problem is…
Reliability in multi-agent systems (MAS) built on large language models is increasingly limited by cognitive failures rather than infrastructure faults. Existing observability tools describe failures but do not quantify how quickly…
We develop model checking algorithms for Temporal Stream Logic (TSL) and Hyper Temporal Stream Logic (HyperTSL) modulo theories. TSL extends Linear Temporal Logic (LTL) with memory cells, functions and predicates, making it a convenient and…
DatalogMTL is an extension of Datalog with metric temporal operators that has found an increasing number of applications in recent years. Reasoning in DatalogMTL is, however, of high computational complexity, which makes reasoning in modern…
This paper describes a technique for inferring temporal-logic properties for sets of finite data streams. Such data streams arise in many domains, including server logs, program testing, and financial and marketing data; temporal-logic…
Latent reasoning enables reasoning over continuous hidden states rather than explicit tokens, avoiding the language bottleneck and inference overhead of chain-of-thought for medical VQA. However, existing methods suffer from modality…
Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and reduce hallucinations. However, developing prompting techniques that enable LLM agents to…
Artificial intelligence (AI) is reshaping strategic planning, with Multi-Agent Reinforcement Learning (MARL) enabling coordination among autonomous agents in complex scenarios. However, its practical deployment in sensitive military…
Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…
This paper presents a novel approach for the Vision-and-Language Navigation (VLN) task in continuous 3D environments, which requires an autonomous agent to follow natural language instructions in unseen environments. Existing end-to-end…
Frontier AI models have achieved remarkable progress, yet recent studies suggest they struggle with compositional reasoning, often performing at or below random chance on established benchmarks. We revisit this problem and show that widely…
A new logic for verification of security policies is proposed. The logic, HyperLTL, extends linear-time temporal logic (LTL) with connectives for explicit and simultaneous quantification over multiple execution paths, thereby enabling…
We introduce Emergent Trust Learning (ETL), a lightweight, trust-based control algorithm that can be plugged into existing AI agents. It enables these to reach cooperation in competitive game environments under shared resources. Each agent…
We propose enhancing the use of propositions for denoting decisions and strategies as established in temporal languages such as CTL*, if interpreted on concurrent game models. The enhancement enables specifying varying coalition structure.…
We present a new strategic logic NCHATL that allows for reasoning about norm compliance on concurrent game structures that satisfy anonymity. We represent such game structures compactly, avoiding models that have exponential size in the…
The remarkable growth in large language model (LLM) capabilities has spurred exploration into multi-agent systems, with debate frameworks emerging as a promising avenue for enhanced problem-solving. These multi-agent debate (MAD)…
Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based,…
The semantics of alternating-time temporal logic (ATL) and the more expressive alternating-time {\mu}-calculus (AMC) is standardly given in terms of concurrent game frames (CGF). The information required to interpret AMC formulas is…
We develop a timeout based extension of propositional linear temporal logic (which we call TLTL) to specify timing properties of timeout based models of real time systems. TLTL formulas explicitly refer to a running global clock together…