HFEPX · Eval paper review
ZenGen Team, Ao Xiang, Bi Jingping, Chen Jiahui +55 more
Published
Jul 26, 2026
Citations
0
Trust level
High
Usefulness score
65/100 (Medium)
Extraction confidence
80% (High)
Derived from extracted protocol signals and abstract evidence.
Rater population
Domain Experts
Signals refreshed
Aug 21, 2026
This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.
Use this as a practical starting point for protocol research, then validate against the original paper.
Best use
Secondary protocol comparison source
Use if you need
A benchmark-and-metrics comparison anchor.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
No major weakness surfaced.
Useful as a secondary reference; validate protocol details against neighboring papers.
If you are doing eval pipeline work, start here
As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track social relations, reason over norms, and adapt behavior under context. This report presents ZenGen, an integrated framework for measuring, internalizing, and grounding social intelligence. For measurement, we introduce SoMBench, a psychology-grounded benchmark spanning 3 primary dimensions, 17 secondary dimensions, and 71 task paradigms. It controls question format, narrative perspective, and context length across 284 shared scenarios and 3,481 expert-verified instances. Evaluation of 20 representative LLMs reveals substantial headroom: the best model achieves only 72.08% overall accuracy, and none of the 17 secondary dimensions reaches the 90% near-ceiling band. For internalization, we develop ZenGen, a diagnosis-driven training recipe combining supervised fine-tuning, on-policy distillation, and rubric-based reinforcement learning. Across five social-cognition benchmarks, ZenGen consistently outperforms its base models, with ZenGen-27B-Stage2 achieving the best average score and ZenGen-32B-Stage2 remaining competitive with DeepSeek-V4-Pro. For deployment-time grounding, we build Actio, a harness-controlled inference architecture that routes four typed supports into reasoning: PRISM for procedural guidance, Starling for runtime mental-state representation, SAGE for reusable experience, and gated RAG for external social and normative knowledge. Across five base models and three benchmarks, the full harness improves 14 of 15 model-benchmark pairs and is best or tied for best in 8, demonstrating the effectiveness of typed runtime support. Together, these results show that socially intelligent LLMs require coordinated advances in evaluation, parametric internalization, and deployment-time grounding.
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
Rubric Rating
Directly usable for protocol triage.
"As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track social relations, reason over norms, and adapt behavior under context."
Automatic Metrics
Includes extracted eval setup.
"As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track social relations, reason over norms, and adapt behavior under context."
Not reported
No explicit QC controls found.
"As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track social relations, reason over norms, and adapt behavior under context."
Sombench
Useful for quick benchmark comparison.
"For measurement, we introduce SoMBench, a psychology-grounded benchmark spanning 3 primary dimensions, 17 secondary dimensions, and 71 task paradigms."
Accuracy, Context length
Useful for evaluation criteria comparison.
"It controls question format, narrative perspective, and context length across 284 shared scenarios and 3,481 expert-verified instances."
Domain Experts
Helpful for staffing comparability.
"It controls question format, narrative perspective, and context length across 284 shared scenarios and 3,481 expert-verified instances."
As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track social relations, reason over norms, and adapt behavior under context.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
Detected: Rubric Rating
Evaluation mode is explicit
Detected: Automatic Metrics
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
Detected: Sombench
Metric reporting is present
Detected: accuracy, context length
