Pursuing Open-Ended Intelligence through
Self-Evolving Synthesis of Verifiable Frontier Tasks
BigBang is a general-purpose large language model evolved from Qwen3.6-35B-A3B through efficient post-training, driven by an adversarial, self-evolving synthetic data framework grounded in verifiable frontier research tasks. BigBang reaches aggregate performance between DeepSeek V4 Flash (284B) and DeepSeek V4 Pro (1.6T).
Problems at the boundary of human knowledge — including those for which no known optimum exists.
Candidate solutions can be assessed using objective rules, formal methods, computational tools, simulators, or experimental feedback.
First in the ∼35B class on 10 of 11 benchmark rows — aggregate performance between DeepSeek V4 Flash (284B) and DeepSeek V4 Pro (1.6T).
Real frontier tasks expose capability gaps; a generator–critic loop turns them into high-quality synthetic data; the trained model is validated on real tasks — and the next round of evolution begins.
Strategy Update · Task Construction
A code agent running a continuous search over programs: it directly modifies, executes, and debugs the data-synthesis code, then refines its generation strategy from critic feedback. An agent harness records motivation, results, and failure causes each round, enabling long-horizon exploration.
Quality Evaluation · Constraint Checks
A two-level adversarial review. Basic constraints — trajectory information, tool-use validity, format integrity — quickly remove degraded outputs. Higher-level evaluation judges evidence, contradiction, verifiability, and research depth: a fast proxy for training value.
Outcome-Calibrated Co-Evolution
Model variants trained on sampled pipelines are evaluated on held-out real research tasks. The meta-critic compares the critic's assessments with observed training outcomes — distinguishing tasks that merely appear difficult from those that genuinely improve capability.
Five head-to-head cases from the paper's §3.3 — every one replayed live.