Related papers: Web Agents Should Adopt the Plan-Then-Execute Para…
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…
AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…
Large language model-based web agents have shown strong potential in automating web interactions through advanced reasoning and instruction following. While retrieval-based memory derived from historical trajectories enables these agents to…
Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we…
LLM-based agents have emerged as promising tools, which are crafted to fulfill complex tasks by iterative planning and action. However, these agents are susceptible to undesired planning hallucinations when lacking specific knowledge for…
Language Model (LM) agents have demonstrated remarkable capabilities in solving tasks that require multiple interactions with the environment. However, they remain vulnerable in environments where a single error often leads to irrecoverable…
Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed.…
Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment. Recent works employ LLMs-as-agents in broadly two ways: iteratively determining the next…
Most web agents operate at the human interface level, observing screenshots or raw DOM trees without application-level access, which limits robustness and action expressiveness. In enterprise settings, however, explicit control of both the…
Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance on dynamic web content, however, makes them vulnerable to prompt injection attacks:…
Assistive agents performing household tasks such as making the bed or cooking breakfast often compute and execute actions that accomplish one task at a time. However, efficiency can be improved by anticipating upcoming tasks and computing…
Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets…
We introduce Mind2Web, the first dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website. Existing datasets for web agents either use simulated…
Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and…
The exceptional capabilities of large language models (LLMs) have substantially accelerated the rapid rise and widespread adoption of agents. Recent studies have demonstrated that generating Python code to consolidate LLM-based agents'…
Recent advances in large language models (LLMs) have enabled agentic systems for sequential decision-making. Such agents must perceive their environment, reason across multiple time steps, and take actions that optimize long-term…
Recent advancements in Large Language Models (LLMs) and multimodal counterparts have spurred significant interest in developing web agents -- AI systems capable of autonomously navigating and completing tasks within web environments. While…
As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted…
What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines reliable multi-step task execution with persistent organizational knowledge learned from…
The development of autonomous machine learning (ML) agents capable of end-to-end data science workflows represents a significant frontier in artificial intelligence. These agents must orchestrate complex sequences of data analysis, feature…