arXiv AI
Toward Agents That Reason About Their Computation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 7
SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning
SpeedrunBench is a new benchmark that tests large language model agents on their ability to develop and refine strategies for completing nine different video games as quickly as possible. The benchmark requires agents to repeatedly improve, reflect, and reason over long action horizons to beat both themselves and other players. Experiments show that while agents can approach human records on simple platformers, they lag behind humans on longer, more complex games within realistic resource limits.
arXiv AI
Jun 19
MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
arXiv:2506. 14990v3 Announce Type: replace Abstract: Benchmarks play a central role in reinforcement learning (RL) research, yet their computational constraints often shape what is studied.
arXiv Machine Learning
Aug 13
Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost
arXiv:2608. 11338v1 Announce Type: cross Abstract: Recently, the practice of augmenting LLM agent capability with skills has gained prevalence.
arXiv AI
Jul 2
Coachable agents for interactive gameplay
arXiv:2607. 00642v1 Announce Type: new Abstract: Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation models.
arXiv Machine Learning
Oct 15
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
arXiv:2610.19789v1 Announce Type: cross Abstract: Self-distillation in agentic reinforcement learning has produced a growing number of methods. However, existing evaluations often reuse published bas...
arXiv AI
Oct 9
Policy Learning with a Language Bottleneck
Policy Learning with a Language Bottleneck (PLLB) is a framework that lets AI agents generate linguistic rules to describe high‑level strategies. PLLB alternates between rule generation, guided by language models, and policy updates that use these rules, even when a single rule cannot fully capture a complex policy. Experiments on five tasks—including a signaling game, maze navigation, image reconstruction, and robot grasp planning—show that PLLB agents learn more interpretable, generalizable behaviors and can share rules with humans for better coordination.