arXiv AI
Schema: Discovering Unknown Environments via Agentic Program Induction
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 8
Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
arXiv:2510. 19771v4 Announce Type: replace Abstract: LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and solve them autonomously.
arXiv AI
Jul 7
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
arXiv:2607. 05174v1 Announce Type: new Abstract: Language agents, i.
arXiv AI
Jul 7
Object-Centric Environment Modeling for Agentic Tasks
arXiv:2607. 02846v1 Announce Type: new Abstract: Large language model (LLM) agents can improve through accumulated experience, but free-form textual memories become difficult to maintain, validate, and reuse as interactions grow.
arXiv AI
Jul 16
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3
arXiv:2607. 01531v2 Announce Type: replace Abstract: Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks.
arXiv AI
Aug 24
AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale
AgentMercury is a scalable framework that synthesizes executable environments from high‑level business scenarios instead of task‑specific benchmarks. It creates a persistent world with entities, services, tools, and invariants, allowing diverse tasks and interaction trajectories to emerge naturally. The authors generated 4,783 environments across 14 industries and 50 countries, and training reinforcement‑learning agents on them improved performance on enterprise workflows and out‑of‑domain benchmarks, while the construction process itself can be learned to increase authoring success.
arXiv Computation and Language
Sep 17
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
arXiv:2609.19134v1 Announce Type: new Abstract: Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain con...