Sakana AI Unveils MASS: A Self-Improving AI Loop Built On Its Own Collective Intelligence
Sakana AI, in collaboration with researchers at UC Berkeley, has introduced Multi-Agent Self-Supervision (MASS), a framework designed to let AI systems keep improving even when tasks become too complex for humans to reliably evaluate. The work addresses a growing problem in AI development: as models move beyond humanity’s accumulated knowledge, human experts may no longer be able to judge or guide their output. MASS tackles this by making the model its own optimizer and evaluator — a form of homogeneous recursive self-improvement — while attempting to avoid the trap of a system reinforcing its own blind spots.
The framework alternates between two loops. In the inner loop, the model organizes copies of itself into a team of virtual subagents governed by a written workflow — specifying each subagent’s role, instructions, contracts for what information must be exchanged, and the order of calls. An orchestrator executes the workflow, an evaluator compares results against the current champion, and an optimizer proposes revisions. In the outer loop, the best-performing multi-agent trajectories are distilled back into the shared model’s weights via fine-tuning, after which the updated model resumes all three roles and the cycle repeats.
After two full cycles starting from a 27B-parameter open-weights model, performance measured as score per output token reached 1.2 to 1.6 times the base model’s level across research benchmarks including MLR-Bench, ScienceAgentBench, DSBench, and AstaBench, with gains confirmed by external judges withheld from the training process.
Key Findings: Dense Signals, Role Generalization, and New Bottlenecks
The researchers report three principal findings. First, MASS enables role generalization: training only on task-solving trajectories improved not just the executor but also the workflow optimizer and evaluator, with agreement between the model’s judgments and strong external judges rising from 73% to 93% across cycles. This suggests the self-improvement loop can sustain itself, since capabilities for producing and selecting future training data improve alongside task performance.
Second, multi-agent trajectories proved substantially more efficient training data than single-agent ones. The model reached a 68.3% win rate over the base using 31% fewer supervised tokens than a comparable single-agent approach — evidence that jointly learning high-level orchestration from orchestrators and bounded execution from subagents provides a denser learning signal per token.
Third, and perhaps most counterintuitive, ablations showed the bottleneck in recursive self-improvement can be the optimizer rather than the evaluator. Swapping in a stronger external model as evaluator alone helped little, but upgrading both evaluator and optimizer let the system find winning workflows for all 12 test tasks within five iterations, compared to 11 of 12 for the fully homogeneous loop, which simply took longer.
Analysis of the evolved workflows revealed that effective coordination shifts task-specific information into contracts and call order — how agents exchange and verify information — rather than roles. The authors emphasize safety implications: in a homogeneous loop, shared blind spots could let flawed results be accepted as progress and reinforced through training, making independent verification mechanisms essential as self-improvement capabilities advance.
Disclaimer
In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.
About The Author
Alisa, a dedicated journalist at the MPost, specializes in crypto, AI, investments, and the expansive realm of Web3. With a keen eye for emerging trends and technologies, she delivers comprehensive coverage to inform and engage readers in the ever-evolving landscape of digital finance.
More articles
Alisa, a dedicated journalist at the MPost, specializes in crypto, AI, investments, and the expansive realm of Web3. With a keen eye for emerging trends and technologies, she delivers comprehensive coverage to inform and engage readers in the ever-evolving landscape of digital finance.
