RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
- Published
- Source
- arXiv
- Paper number
- 1180
- Field
- Agents
- arXiv ID
- 2610.10507
Key points
- They formalized the problem of deriving evidence through filtering, aggregation, and computation rather than mere retrieval as a sequential decision process.
- RouterLM alternates between calling primitive operations and synthesizing custom code to build evidence, trained with SFT and GRPO.
- It achieved a 75.6% mean success rate across six heterogeneous benchmarks, 15.9 percentage points above the strongest baseline.
- The compact 9B trained model outperformed a training-free Gemini 3.5 Flash router by 5.0 percentage points.
- On three unseen benchmarks it stayed 15.0 percentage points ahead on average, demonstrating zero-shot generalization.
Paper links
External research summaries. These are not HDATF publications or measured product results.