Related papers: CP-Agent: A Calibrated Risk-Controlled Agent for F…

If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling evidence arises when the model itself freely reproduces the target content. As such, we propose…

Large Language Models (LLMs) achieve competitive results compared to human experts in medical examinations. However, it remains a challenge to apply LLMs to complex clinical decision-making, which requires a deep understanding of medical…

LLM-based multi-agent systems can fail even when planned actions are executed correctly because agents may misjudge their knowledge when evaluating plan feasibility, a phenomenon we term epistemic miscalibration in planning. Unlike…

While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak. The integration of Large Language Models (LLMs) with external tools via protocols such as the Model Context Protocol (MCP)…

Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…

LLM-based tools are automating more software development tasks at a rapid pace, but there is no rigorous way to evaluate how different architectural choices -- prompts, skills, tools, multi-agent setups -- materially affect both capability…

Students benefit from math problems contextualized to their interests. Large language models (LLMs) offer promise for efficient personalization at scale. However, LLM-generated personalized problems may often have problems such as…

Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated against human annotation. We introduce AgentProp-Bench, a 2,000-task benchmark with 2,300…

Large language model(LLM)-driven multi-agent systems(MAS) coordinate specialized agents through predefined interaction topologies and have shown promise for complex tasks such as competition-level code generation. Recent studies demonstrate…

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…

Large Language Models (LLMs) demonstrate strong potential for automated code generation, yet their ability to iteratively refine solutions using execution feedback remains underexplored. Competitive programming offers an ideal testbed for…

The advent of strong generative AI has a considerable impact on various software engineering tasks such as code repair, test generation, or language translation. While tools like GitHub Copilot are already in widespread use in interactive…

Cooperative multi-agent reinforcement learning (c-MARL) is widely applied in safety-critical scenarios, thus the analysis of robustness for c-MARL models is profoundly important. However, robustness certification for c-MARLs has not yet…

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…

Mathematical modeling is a cornerstone of scientific discovery and engineering practice, enabling the translation of real-world problems into formal systems across domains such as physics, biology, and economics. Unlike mathematical…

Large language models (LLMs) exhibit strong reasoning and conversational abilities, but ensuring reliable behavior in multi-turn interactions remains challenging. In many real-world applications, agents must succeed in one-shot settings…

When Model Predictive Control (MPC) is used in real-time to control linear systems, quadratic programs (QPs) need to be solved within a limited time frame. Recently, several parametric methods have been proposed that certify the number of…

Large Language Models (LLMs), such as GPT-4, have demonstrated impressive mathematical reasoning capabilities, achieving near-perfect performance on benchmarks like GSM8K. However, their application in personalized education remains limited…

In industrial control systems, the generation and verification of Programmable Logic Controller (PLC) code are critical for ensuring operational efficiency and safety. While Large Language Models (LLMs) have made strides in automated code…

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…