Pith. sign in

REVIEW 15 cited by

Benchmarking the Spectrum of Agent Capabilities

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 2109.06780 v2 pith:AN373RUL submitted 2021-09-14 cs.AI cs.LG

Benchmarking the Spectrum of Agent Capabilities

classification cs.AI cs.LG
keywords agentsabilitiescrafterrewardachievementsenvironmentenvironmentsevaluating
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Evaluating the general abilities of intelligent agents requires complex simulation environments. Existing benchmarks typically evaluate only one narrow task per environment, requiring researchers to perform expensive training runs on many different environments. We introduce Crafter, an open world survival game with visual inputs that evaluates a wide range of general abilities within a single environment. Agents either learn from the provided reward signal or through intrinsic objectives and are evaluated by semantically meaningful achievements that can be unlocked during each episode, such as discovering resources and crafting tools. Consistently unlocking all achievements requires strong generalization, deep exploration, and long-term reasoning. We experimentally verify that Crafter is of appropriate difficulty to drive future research and provide baselines scores of reward agents and unsupervised agents. Furthermore, we observe sophisticated behaviors emerging from maximizing the reward signal, such as building tunnel systems, bridges, houses, and plantations. We hope that Crafter will accelerate research progress by quickly evaluating a wide spectrum of abilities.

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. Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

    cs.CL 2023-09 unverdicted novelty 8.0

    Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.

  2. Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Better Model Faithfulness

    cs.AI 2026-05 unverdicted novelty 7.0

    FAX uses explicit claim verification against faithful tools to raise simulation faithfulness from 0.20 to 0.46 on the new CRAFTER-XAI-Bench open-world RL benchmark.

  3. ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders

    cs.RO 2026-05 unverdicted novelty 7.0

    ARC-RL provides four new MuJoCo continuous-control environments with hexapod and quadruped morphologies inspired by ARC Raiders, a unified multi-component reward without motion capture, CPG expert demonstrators, and e...

  4. MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs

    cs.AI 2026-05 unverdicted novelty 7.0

    MAGE uses a four-subgraph co-evolutionary knowledge graph plus dual bandits to externalize and retrieve experience for stable self-evolution of frozen language-model agents, showing gains on nine diverse benchmarks.

  5. PACE: Parameter Change for Unsupervised Environment Design

    cs.LG 2026-05 unverdicted novelty 7.0

    PACE uses the squared L2 norm of policy parameter changes from a first-order approximation as an efficient proxy for environment value in UED, outperforming baselines with higher IQM and lower optimality gap on MiniGr...

  6. Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games

    cs.AI 2025-06 unverdicted novelty 7.0

    Orak is a foundational benchmark providing training data, interfaces, and evaluation tools for LLM agents across diverse video game genres.

  7. Mastering Diverse Domains through World Models

    cs.AI 2023-01 unverdicted novelty 7.0

    DreamerV3 uses world models and robustness techniques to solve over 150 tasks across domains with a single configuration, including Minecraft diamond collection from scratch.

  8. AutoMem: Automated Learning of Memory as a Cognitive Skill

    cs.AI 2026-07 unverdicted novelty 6.0

    AutoMem automates memory structure revision and proficiency training in LLMs, delivering 2x-4x performance gains on long-horizon games without altering task-action behavior.

  9. APPO: Agentic Procedural Policy Optimization

    cs.LG 2026-06 unverdicted novelty 6.0

    APPO refines branching and credit assignment in agentic RL via a Branching Score and procedure-level scaling, improving baselines by nearly 4 points on 13 benchmarks.

  10. CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization

    cs.RO 2026-06 unverdicted novelty 6.0

    CLAW is an end-to-end self-supervised method that learns semantically meaningful continuous latent actions and predictive world models from action-free videos to support imitation learning and goal-directed planning.

  11. Goal-Conditioned Agents that Learn Everything All at Once

    cs.LG 2026-05 unverdicted novelty 6.0

    LEO enables efficient all-goals learning in goal-conditioned RL by jointly predicting for all goals in one network pass, yielding >250x speedup over relabelling and better performance on Craftax.

  12. ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders

    cs.RO 2026-05 accept novelty 6.0

    ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical c...

  13. 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.

  14. TRAP: Tail-aware Ranking Attack for World-Model Planning

    cs.LG 2026-05 unverdicted novelty 6.0

    TRAP is a tail-aware ranking attack that plants a backdoor in world models so that a trigger causes the model to reorder a few critical imagined trajectories and redirect planning while preserving normal behavior on c...

  15. Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction

    cs.LG 2026-03 unverdicted novelty 6.0

    Dreamer-CDP achieves reconstruction-free world modeling via a JEPA-style predictor on continuous deterministic representations and matches Dreamer's performance on Crafter.