Related papers: Abduct, Act, Predict: Scaffolding Causal Inference…
Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…
AI-assisted task delegation is increasingly common, yet human effort in such systems is costly and typically unobserved. Recent work by Bastani and Cachon (2025); Sambasivan et al. (2021) shows that accuracy-based payment schemes suffer…
Abduction is the task of computing a sufficient extension of a knowledge base (KB) that entails a conclusion not entailed by the original KB. It serves to compute explanations, or hypotheses, for such missing entailments. While this task…
Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors: a single faulty step can propagate across agents and disrupt the trajectory. In this paper, we present MASC,…
AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…
Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective antidote by randomly dropping a proportion of units,…
Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic…
While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information from individual agents. Current solutions often resort to rigid structural engineering or expensive fine-tuning,…
The recent adoption of machine learning as a tool in real world decision making has spurred interest in understanding how these decisions are being made. Counterfactual Explanations are a popular interpretable machine learning technique…
Large Language Models (LLMs) enhanced with retrieval -- commonly referred to as Retrieval-Augmented Generation (RAG) -- have demonstrated strong performance in knowledge-intensive tasks. However, RAG pipelines often fail when retrieved…
Large language models (LLMs) have shown strong potential in automating the design of agentic workflows. However, existing methods still rely heavily on manually predefined operators, limiting generalization and scalability. To address this…
Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attribution is therefore critical, but existing approaches, such…
Ad hoc teamwork refers to the problem of enabling an agent to collaborate with teammates without prior coordination. Data-driven methods represent the state of the art in ad hoc teamwork. They use a large labeled dataset of prior…
Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…
Logic-based abduction finds important applications in artificial intelligence and related areas. One application example is in finding explanations for observed phenomena. Propositional abduction is a restriction of abduction to the…
In task-oriented dialogue, a system often needs to follow a sequence of actions, called a workflow, that complies with a set of guidelines in order to complete a task. In this paper, we propose the novel problem of multi-step workflow…
Language agents have demonstrated autonomous decision-making abilities by reasoning with foundation models. Recently, efforts have been made to train language agents for performance improvement, with multi-step reasoning and action…
Error attribution in Large Language Model (LLM) multi-agent systems presents a significant challenge in debugging and improving collaborative AI systems. Current approaches to pinpointing agent and step level failures in interaction traces…
Classifying the general intent of the user utterance in a conversation, also known as Dialogue Act (DA), e.g., open-ended question, statement of opinion, or request for an opinion, is a key step in Natural Language Understanding (NLU) for…
Much of the reported progress in file-level software defect prediction (SDP) is, in reality, nothing but an illusion of accuracy. Over the last decades, machine learning and deep learning models have reported increasing performance across…