Pith. sign in

REVIEW 15 cited by

Scaling Instructable Agents Across Many Simulated Worlds

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.10179 v3 pith:CBWYKIRO submitted 2024-03-13 cs.RO cs.AIcs.HCcs.LG

Scaling Instructable Agents Across Many Simulated Worlds

classification cs.RO cs.AIcs.HCcs.LG
keywords environmentsagentslanguageacrossgoalinstructableinstructionsaccomplish
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI. Accomplishing this goal requires learning to ground language in perception and embodied actions, in order to accomplish complex tasks. The Scalable, Instructable, Multiworld Agent (SIMA) project tackles this by training agents to follow free-form instructions across a diverse range of virtual 3D environments, including curated research environments as well as open-ended, commercial video games. Our goal is to develop an instructable agent that can accomplish anything a human can do in any simulated 3D environment. Our approach focuses on language-driven generality while imposing minimal assumptions. Our agents interact with environments in real-time using a generic, human-like interface: the inputs are image observations and language instructions and the outputs are keyboard-and-mouse actions. This general approach is challenging, but it allows agents to ground language across many visually complex and semantically rich environments while also allowing us to readily run agents in new environments. In this paper we describe our motivation and goal, the initial progress we have made, and promising preliminary results on several diverse research environments and a variety of commercial video games.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries

    cs.SE 2026-05 conditional novelty 7.0

    SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round rep...

  2. Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks

    cs.AI 2026-04 unverdicted novelty 7.0

    COSPLAY co-evolves an LLM decision agent with a skill bank agent to improve long-horizon game performance, reporting over 25.1% average reward gains versus frontier LLM baselines on single-player benchmarks.

  3. Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time

    cs.CV 2026-04 unverdicted novelty 7.0

    PokeGym is a new benchmark that tests VLMs on long-horizon tasks in a complex 3D game using only visual observations, identifying deadlock recovery as the primary failure mode.

  4. RetroMotion: Retrocausal Motion Forecasting Models are Instructable

    cs.CV 2025-05 unverdicted novelty 7.0

    Retrocausal transformer decomposes multi-agent motion forecasts into marginals and pairwise joints, models uncertainty with compressed exponentials, achieves strong Waymo results, generalizes to Argoverse 2 and V2X-Se...

  5. SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents

    cs.CV 2026-05 unverdicted novelty 6.0

    SPIKE dual-controller framework raises success rates 5-9 points and cuts tokens 55% in StarDojo agents by reusing strategic plans across stable segments and escalating only at detected events.

  6. CA2: Code-Aware Agent for Automated Game Testing

    cs.SE 2026-05 unverdicted novelty 6.0

    CA2 integrates call stack information into RL agents for game testing and shows consistent gains over baselines that ignore code signals.

  7. Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 6.0

    Odysseus adapts PPO with a turn-level critic and leverages pretrained VLM action priors to train agents achieving at least 3x average game progress over frontier models in long-horizon Super Mario Land.

  8. Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time

    cs.CV 2026-04 reject novelty 6.0

    The manuscript body introduces PokeGym, a vision-only automated 3D-game benchmark, while the abstract claims a G-EvoMAC method and 60.18% success rate absent from the body.

  9. Update-Free On-Policy Steering via Verifiers

    cs.RO 2026-03 conditional novelty 6.0

    Lightweight verifiers trained on a diffusion policy’s own evaluation rollouts raise real-robot success rates ~49% on average via Best-of-N or classifier guidance, without changing base parameters.

  10. Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse

    cs.CV 2026-05 unverdicted novelty 5.0

    The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.

  11. Video Game Accessibility through Shared Control for People with Upper-Limb Impairments

    cs.HC 2026-01 unverdicted novelty 5.0

    A configurable framework called GamePals enables shared control via human cooperation or partial automation to improve video game accessibility for people with upper-limb impairments, evaluated in a study with 13 part...

  12. UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

    cs.AI 2025-09 conditional novelty 5.0

    UI-TARS-2 reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld while attaining 59.8 mean normalized score on a 15-game suite through multi-turn RL and scalable data generation.

  13. AGI Requires a Coordination Layer on Top of Pattern Repositories

    cs.AI 2025-12 reject novelty 4.0

    The paper claims AGI requires a System-2 coordination layer on top of LLM pattern repositories, formalized by an anchoring score S = ρd − dr − γ log k.

  14. Shared Control for Game Accessibility: Understanding Current Human Cooperation Practices to Inform the Design of Partial Automation Solutions

    cs.HC 2025-09 unverdicted novelty 4.0

    Interviews with 14 accessible gamers identify essential shared-control practices, key limitations of human assistance, and design requirements for software agents that could automate support.

  15. Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse

    cs.CV 2026-05 unverdicted novelty 3.0

    This work traces four eras of generalist game players across dataset, model, harness, and benchmark pillars and charts a five-level roadmap ending in agents that create and evolve within game multiverses.