ForkPilot Cuts Tokens by 59%
New framework optimizes long-horizon agent search via self-evolving policy, significantly reducing token costs while maintaining performance.
ImportanceMaterialEvidenceE2 unreplicatedWrite-upQuick
The ForkPilot framework achieves up to 59.2% token reduction in long-horizon agent tasks while maintaining state-of-the-art performance.
Traditional agents often struggle with retrospective search due to delayed outcomes causing attribution complexity and stale estimates from evolving execution evidence. ForkPilot introduces Search Value Dynamics (SVD) and uses a two-stage self-evolving policy: learning offline from completed trajectories, then making real-time decisions and updating itself.
Evaluated across 6 benchmarks and 7 LLM backbones (including GPT-5.6 Sol and Opus 4.8) against 9 baselines, the study reports significant efficiency gains. Note that these results come from a preprint and await independent reproduction.