Related papers: Perfect score on IPhO 2025 theory by Gemini agent

AI agents powered by large language models exhibit strong reasoning and problem-solving capabilities, enabling them to assist scientific research tasks such as formula derivation and code generation. However, whether these agents can…

It is astonishing how rapidly general-purpose AI has crossed familiar thresholds in introductory physics. Comparing outputs from successive models, GPT-5 Thinking moves far beyond the plug-and-chug tendencies seen earlier: on a classic…

Using AI to write formal proofs for mathematical problems is a challenging task that has seen some advancements in recent years. Automated systems such as Lean can verify the correctness of proofs written in formal language, yet writing the…

Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The…

We present a proximal policy optimization (PPO) agent trained through curriculum learning (CL) principles and meticulous reward engineering to optimize a real-world high-throughput waste sorting facility. Our work addresses the challenge of…

Proximal Policy Optimization (PPO) is a ubiquitous on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings. This is often due to the belief that PPO is…

We formulate a problem on diamagnetic levitation, which may be suitable for specialized high-school or first-year students in physical sciences. We guide the students, step-by-step, through the physics of diamagnetic levitation. The…

In this paper, we tackle the important yet under-investigated problem of making long-horizon prediction of event sequences. Existing state-of-the-art models do not perform well at this task due to their autoregressive structure. We propose…

This paper describes a competition proposal for evolving Intelligent Agents for the game-playing framework called EvoMan. The framework is based on the boss fights of the game called Mega Man II developed by Capcom. For this particular…

In this paper, we describe our winning approach to solving the Lane Following Challenge at the AI Driving Olympics Competition through imitation learning on a mixed set of simulation and real-world data. AI Driving Olympics is a two-stage…

"Theorem proving is similar to the game of Go. So, we can probably improve our provers using deep learning, like DeepMind built the super-human computer Go program, AlphaGo." Such optimism has been observed among participants of AITP2017.…

Reinforcement Learning, a machine learning framework for training an autonomous agent based on rewards, has shown outstanding results in various domains. However, it is known that learning a good policy is difficult in a domain where…

Hyperparameter optimization (HPO) is a critical yet challenging aspect of machine learning model development, significantly impacting model performance and generalization. Traditional HPO methods often struggle with high dimensionality,…

State-of-the-art (SOTA) LLMs have progressed from struggling on proof-based Olympiad problems to solving most of the IMO 2025 problems, with leading systems reportedly handling 5 of 6 problems. Given this progress, we assess how well these…

To advance the field of autonomous robotics, particularly in object search tasks within unexplored environments, we introduce a novel framework centered around the Probable Object Location (POLo) score. Utilizing a 3D object probability…

Reinforcement Learning agents are expected to eventually perform well. Typically, this takes the form of a guarantee about the asymptotic behavior of an algorithm given some assumptions about the environment. We present an algorithm for a…

We present AlphaGeometry2 (AG2), a significantly improved version of AlphaGeometry introduced in (Trinh et al., 2024), which has now surpassed an average gold medalist in solving Olympiad geometry problems. To achieve this, we first extend…

I discuss issues of inverting feasibly computable functions, optimal discovery algorithms, and the constant overheads in their performance.

Despite recent breakthroughs, the ability of deep learning and reinforcement learning to outperform traditional approaches to control physically embodied robotic agents remains largely unproven. To help bridge this gap, we created the 'AI…

The concept of an embodied intelligent agent is a key concept in modern artificial intelligence and robotics. Physically, an agent is an open system embedded in an environment that it interacts with through sensors and actuators. It…