arXiv:2609.14473v1 Announce Type: new Abstract: Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical...
arXiv:2608. 14851v1 Announce Type: new Abstract: Learning and skill mastery require extensive and deliberate practice.
arXiv:2609.09059v1 Announce Type: new Abstract: While many video-game environments (VGEs) have played crucial roles in advancing reinforcement learning (RL), developing novel VGEs or modifying existi...
GameGo is a framework that converts short game ideas into detailed Product Requirements Documents using industry practices, enabling coding agents to generate complete games from sparse user queries. It employs dynamic compression to keep essential gameplay constraints while allowing design flexibility. The authors built GameGoData with over 55,000 development trajectories and GameGoBench with 124 game queries, training GameGoCoder to outperform baselines and match leading models on gamedev benchmarks.
arXiv:2607. 05185v1 Announce Type: new Abstract: Compositional generalization, the ability to understand and produce novel combinations of known components, remains a fundamental challenge for modern artificial intelligence.
InternBootcamp is an open‑source framework that offers over 1,000 domain‑diverse task environments for large language model (LLM) reasoning research. It introduces Bootcamp‑Eval, an automatically generated benchmark for comprehensive performance assessment. Experiments show that training on InternBootcamp significantly improves reasoning performance, with a 32B model achieving state‑of‑the‑art results on Bootcamp‑Eval and other established benchmarks, demonstrating that scaling the number of training tasks yields consistent gains.
The paper introduces MIMIC, a framework that uses executable code to generate rigorous reasoning data for large language models (LLMs). By converting algorithms into verifiable reasoning trajectories through narrative fusion, code-guided test synthesis, and dynamic code instrumentation, MIMIC creates a Code-Instrumented Reward (CIR) that supplies dense, high‑fidelity supervision for reinforcement learning. Models trained with MIMIC’s synthetic dataset show significant, consistent improvements in general reasoning, complex mathematics, and fine‑grained deterministic tasks.
arXiv:2607. 00248v1 Announce Type: new Abstract: We present Seed2.
arXiv:2510. 01764v3 Announce Type: replace Abstract: Reinforcement learning (RL) research requires diverse, challenging environments that are both tractable and scalable.
arXiv:2108.11204v4 Announce Type: replace-cross Abstract: Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propo...
The paper introduces a method for creating reactive character behaviors in continuous games as compact, human‑readable programs. It searches over a domain‑specific language that uses reactive geometric decisions and higher‑order constructs to discretize continuous behavior space, while eliminating redundant program forms through synthesis antipatterns. The approach, called agentic sketching, combines bottom‑up symbolic enumeration with top‑down guidance from a coding agent, and outperforms either technique alone on a benchmark of 14 continuous games.
arXiv:2606. 29929v1 Announce Type: new Abstract: Distilling historical trajectories into reusable experience to enhance future problem-solving has become a focal point of recent LLM research.