Related papers: DISCOVERYWORLD: A Virtual Environment for Developi…
Progress in scientific discovery is rarely the result of a single "Eureka" moment, but is rather the product of hundreds of scientists incrementally working together toward a common goal. While existing agent workflows are capable of…
Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (LLMs) in automating…
Frontier AI agents show increasing promise as scientific research assistants, and may eventually be useful for extended, open-ended research workflows. However, in order to use agents for novel research, we must first assess the underlying…
General virtual agents need to handle multimodal observations, master complex action spaces, and self-improve in dynamic, open-domain environments. However, existing environments are often domain-specific and require complex setups, which…
The aim of my Ph.D. thesis concerns Reasoning in Highly Reactive Environments. As reasoning in highly reactive environments, we identify the setting in which a knowledge-based agent, with given goals, is deployed in an environment subject…
As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can (1) learn by themselves continually in a self-motivated and self-initiated manner rather than being…
Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attention, and beneath them lie the values silently steering agent…
Search agents are language models (LMs) that reason and search knowledge bases (or the web) to answer questions; recent methods supervise only the final answer accuracy using reinforcement learning with verifiable rewards (RLVR). Most RLVR…
Artificial intelligence (AI) agents are emerging as transformative tools in drug discovery, with the ability to autonomously reason, act, and learn through complicated research workflows. Building on large language models (LLMs) coupled…
Graphical User Interface (GUI) agents show strong capabilities for automating web tasks, but existing interactive benchmarks primarily target benign, predictable consumer environments. Their effectiveness in high-stakes, investigative…
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…
Scientific discovery increasingly entails long-horizon exploration of complex hypothesis spaces, yet most existing approaches emphasize final performance while offering limited insight into how scientific exploration unfolds over time,…
Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing environment generation methods often emphasize visual realism (e.g., object diversity and layout…
We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection…
Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings. Yet existing data science benchmarks fall short due to fragmented evaluation interfaces that make…
Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended…
In scientific research, analysis requires accurately interpreting complex multimodal knowledge, integrating evidence from different sources, and drawing inferences grounded in domain-specific knowledge. However, current artificial…
We introduce NeoWorld, a deep learning framework for generating interactive 3D virtual worlds from a single input image. Inspired by the on-demand worldbuilding concept in the science fiction novel Simulacron-3 (1964), our system constructs…
AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this…
AI models underpin data-centric applications from image and text processing to scientific discovery in biology, physics, and chemistry. Yet developing them remains heavily manual, requiring practitioners to design architectures, build…