Pith. sign in

REVIEW 7 cited by

Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

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 2010.09890 v2 pith:4R3OIYEJ submitted 2020-10-19 cs.AI cs.LGcs.MA

classification cs.AIcs.LGcs.MA
keywords agentchallengehuman-likesocialtaskenvironmentagentscollaboration
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper, we introduce Watch-And-Help (WAH), a challenge for testing social intelligence in agents. In WAH, an AI agent needs to help a human-like agent perform a complex household task efficiently. To succeed, the AI agent needs to i) understand the underlying goal of the task by watching a single demonstration of the human-like agent performing the same task (social perception), and ii) coordinate with the human-like agent to solve the task in an unseen environment as fast as possible (human-AI collaboration). For this challenge, we build VirtualHome-Social, a multi-agent household environment, and provide a benchmark including both planning and learning based baselines. We evaluate the performance of AI agents with the human-like agent as well as with real humans using objective metrics and subjective user ratings. Experimental results demonstrate that the proposed challenge and virtual environment enable a systematic evaluation on the important aspects of machine social intelligence at scale.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue

    cs.MA 2026-05 unverdicted novelty 7.0 of 10

    Dialogue between partially-observing LLM agents cuts action conflicts by 40-83 points but lowers task success versus silent coordination, with new metrics exposing limited genuine world-model alignment.

  2. R^3-VQA: "Read the Room" by Video Social Reasoning

    cs.CV 2025-05 conditional novelty 7.0 of 10

    R3-VQA is a new real-world video benchmark on which the best tested model, GPT-4o, scores 83% on generated questions but only 54% on human-written ones, while humans score 91% and 80%.

  3. CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views

    cs.CV 2026-07 accept novelty 6.5 of 10

    CoMind releases 41 h of synchronized multi-view cooking collaboration with social-cue annotations and three ToM-oriented benchmarks on which current VLMs score poorly until fine-tuned.

  4. CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Topology-aware attention over hierarchical scene graphs lets a 3D-LLM ground, caption, and answer questions across multi-room homes, with large gains on a new HM3D benchmark.

  5. Human-AI Collaboration for Estimating Scientific Replicability

    cs.CY 2026-04 conditional novelty 6.0 of 10

    Hybrid human-AI prediction markets match or slightly outperform AI-only markets at forecasting scientific replication outcomes across six social science disciplines.

  6. Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant

    cs.CL 2025-04 conditional novelty 5.0 of 10

    Auto-SLURP is a new end-to-end benchmark for LLM multi-agent personal assistants, and the best current framework still fails a majority of user requests.

  7. Large Language Models for Planning: A Comprehensive and Systematic Survey

    cs.AI 2025-05 conditional novelty 3.0 of 10

    A structured survey of LLM planning methods, benchmarks, and interpretability work, organized around a three-way taxonomy.

Pith tools