Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet Traces
Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes. Leading recipes (RLVR, group-relative RL, rejection-sampled re-SFT) all need multi-turn traces carrying per-trajectory supervision, and the two existing sources fall short: frontier-synthesised data inherits the synthesizer's biases and collapses the long tail, while unfiltered production logs are unjudged and contaminated by shortcut behaviour. We argue that an incentive-aligned agent arena can be engineered to manufacture such trajectories, and demonstrate this on ORO Subnet 15 (SN15), a Bittensor deployment of the ShoppingBench agentic-commerce benchmark. SN15's race me...
| Authors | Shardul Bansal, Seth Schilbe, Jarrod Barnes |
|---|---|
| Primary category | cs.LG |
| Published | 8 June 2026 |
| Last updated at source | 8 June 2026 |
Connected in the knowledge graph
- oro-ai/sn15-shoppingbench-sft-15kDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.