Related papers: Conditional Multi-Stage Failure Recovery for Embod…
AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which…
Learning a perception and reasoning module for robotic assistants to plan steps to perform complex tasks based on natural language instructions often requires large free-form language annotations, especially for short high-level…
A multi-agent pipeline with N agents typically issues N LLM calls per run. Merging agents into fewer calls (compound execution) promises token savings, but naively merged calls silently degrade quality through tool loss and prompt…
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…
Large language models (LLMs) have demonstrated significant advancements in error handling. Current error-handling works are performed in a passive manner, with explicit error-handling instructions. However, in real-world scenarios, explicit…
Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: open-loop methods that compile tasks into formal representations for external executors produce sound plans but lack adaptability in…
Large Language Models (LLMs) are increasingly used for decision making in embodied agents, yet existing safety evaluations often rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these…
Recent advances in multimodal agents have improved computer-use interaction and tool-usage, yet most existing systems remain reactive, optimizing actions in isolation without reasoning about future states or long-term goals. This limits…
Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…
Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly…
We study the asymptotic performance of the Thompson sampling algorithm in the batched multi-armed bandit setting where the time horizon $T$ is divided into batches, and the agent is not able to observe the rewards of her actions until the…
Training LLMs on decentralized nodes or on-spot instances, lowers the training cost and enables model democratization. The inevitable challenge here is the transient churns of nodes due to failures and the operator's scheduling policies,…
Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…
The performance of large language models (LLMs) depends on how they are prompted, with choices spanning both the high-level prompting pattern (e.g., Zero-Shot, CoT, ReAct, ReWOO) and the specific prompt content (instructions and few-shot…
Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory architecture comprising six cognitive mechanisms: (1) sleep-phase consolidation, (2)…
Large language models are increasingly used as natural-language interfaces to enterprise software, but their direct use as system operators remains unsafe. Model errors can propagate into unauthorized actions, malformed requests,…
Multi-UAV air combat is a complex task involving multiple autonomous UAVs, an evolving field in both aerospace and artificial intelligence. This paper aims to enhance adversarial performance through collaborative strategies. Previous…
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,…
In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and solving mathematical problems, leading to advancements in various fields. We propose an LLM-embodied path planning framework for…
LLM-based approaches have recently achieved impressive results in zero-shot stance detection. However, they still struggle in complex real-world scenarios, where stance understanding requires dynamic background knowledge, target definitions…