Related papers: PALADIN: Self-Correcting Language Model Agents to …

Large Language Models (LLMs) have achieved impressive results across numerous NLP tasks but still encounter difficulties in machine translation. Traditional methods to improve translation have typically involved fine-tuning LLMs using…

Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks. In real-world applications, user…

This paper presents an approach towards specifying and verifying adaptive distributed systems. We here take fault-handling as an example of adaptive behavior and propose a modeling language Sandal for describing fault-prone message-passing…

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…

This paper introduces a framework that integrates reinforcement learning (RL) with autonomous agents to enable continuous improvement in the automated process of software test cases authoring from business requirement documents within…

With the rapid development of large language models, the potential threat of their malicious use, particularly in generating phishing content, is becoming increasingly prevalent. Leveraging the capabilities of LLMs, malicious users can…

Large language models (LLMs) remain unreliable for global enterprise applications due to substantial performance gaps between high-resource and mid/low-resource languages, driven by English-centric pretraining and internal reasoning biases.…

Large Language Models (LLMs) enhance their problem-solving capability by utilizing external tools. However, in open-world scenarios with massive and evolving tool repositories, existing methods relying on static embedding retrieval or…

Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). However, careful evaluations by human reveal that the translations produced by LLMs still contain multiple errors. Importantly, feeding back such…

External tool integration through function-calling is essential for practical language model applications, yet most multilingual models lack reliable tool-use capabilities in non-English languages. Even state-of-the-art multilingual models…

Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks. Due to the limited context length of tool-using LLMs, adopting information retrieval (IR) models to…

Large language models (LLMs) have achieved remarkable progress in complex reasoning tasks, yet they remain fundamentally limited by their reliance on static internal knowledge and text-only reasoning. Real-world problem solving often…

Tool-using LLM agents fail through trajectories rather than only final responses, as they may execute unsafe tool calls, follow injected instructions, comply with harmful requests, or over-refuse benign tasks despite producing a seemingly…

The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To…

While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce…

The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges.…

Reasoning about failures is crucial for building reliable and trustworthy robotic systems. Prior approaches either treat failure reasoning as a closed-set classification problem or assume access to ample human annotations. Failures in the…

Small language models are attractive for production deployment due to their low cost, fast inference, and ease of specialization. However, adapting them to a specific task remains a challenging engineering loop, driven not by training…

Post-training algorithms based on deep reinforcement learning can push the limits of robotic models for specific objectives, such as generalizability, accuracy, and robustness. However, Intervention-requiring Failures (IR Failures) (e.g., a…

Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance…