Related papers: AI Scientist via Synthetic Task Scaling
Recent advancements in large language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios. In order to achieve success in long…
Tool-augmented LLMs are a promising approach to create AI agents that can have realistic conversations, follow procedures, and call appropriate functions. However, evaluating them is challenging due to the diversity of possible…
LLM agents have demonstrated remarkable capabilities in software development, but their performance is hampered by long interaction contexts, which incur high API costs and latency. While various context compression approaches such as…
Many challenges remain before AI agents can be deployed in real-world environments. However, one virtue of such environments is that they are inherently multi-agent and contain human experts. Using advanced social intelligence in such an…
Enabling Large Language Models (LLMs) to effectively utilize tools in multi-turn interactions is essential for building capable autonomous agents. However, acquiring diverse and realistic multi-turn tool-use data remains a significant…
In automated crop protection tasks such as weed control, disease diagnosis, and pest monitoring, deep learning has demonstrated significant potential. However, these advanced models rely heavily on high-quality, diverse datasets, often…
Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE). Recent LLM-powered toolkits, such as OpenAI Codex and Cursor, have…
Much previous AI research has focused on developing monolithic models to maximize their intelligence, with the primary goal of enhancing performance on specific tasks. In contrast, this work attempts to study using LLM-based agents to…
LLMs and Agents have achieved impressive progress in code generation, mathematical reasoning, and scientific discovery. However, existing benchmarks primarily measure correctness, overlooking the diversity of methods behind solutions. True…
Solving complex real-world tasks requires cycles of actions and observations. This is particularly true in science, where tasks require many cycles of analysis, tool use, and experimentation. Language agents are promising for automating…
In the realm of education, student evaluation holds equal significance to imparting knowledge. To be evaluated, students usually need to go through text-based academic assessment methods. Instructors need to make a diverse set of questions…
As data-science agents shift from co-pilots to auto-pilots, silent misframing becomes a critical failure mode. Agents quietly commit to plausible but unintended task framings, producing clean, executable artifacts that hide their incorrect…
Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments are expensive to build, brittle to extend, and fundamentally limited in diversity. A…
The rapid adoption of AI agents across domains has made systematic evaluation crucial for ensuring their usefulness and successful production deployment. Evaluation of AI agents typically involves using a fixed set of benchmarks and…
Recent progress in large language models (LLMs) has enabled tool-augmented agents capable of solving complex real-world tasks through step-by-step reasoning. However, existing evaluations often focus on general-purpose or multimodal…
Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks. However, applying them for complex, multi-step, long-horizon tasks remains a challenge. Recent work have found success by…
As agent capabilities advance, existing benchmarks, such as $\tau^2$-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remains complex, costly, and labor-intensive. Moreover, the standard approach, in which…
Recent advancements in large language model (LLM) agents have significantly accelerated scientific discovery automation, yet concurrently raised critical ethical and safety concerns. To systematically address these challenges, we introduce…
Agent-based models (ABMs) simulate interactions between autonomous agents in constrained environments over time. ABMs are often used for modeling the spread of infectious diseases. In order to simulate disease outbreaks or other phenomena,…
The automation of scientific discovery represents a critical milestone in Artificial Intelligence (AI) research. However, existing agentic systems for science suffer from two fundamental limitations: rigid, pre-programmed workflows that…