# Navalia improves cowork agent performance over Qwen3.6-35B-A3B on finance benchmarks

Digest AI · Research · published 2026-10-21T04:00:00Z

Canonical: https://digestai.news/story/navalia-improves-cowork-agent-performance-over-qwen3-6-35b-a3b-on-fina

## Summary

Researchers present Navalia, a framework that equips cowork agents with verifiable task synthesis and long‑horizon post‑training. The system draws on corporate financial reports, selects supporting evidence, and builds executable computation chains that create multi‑step analytical tasks with traceable data dependencies. Independent LLM reviews and programmatic checks verify evidence consistency and answer correctness before the tasks are used for trajectory collection.

Navalia fine‑tunes a base Qwen3.6-35B-A3B model through supervised fine‑tuning and reinforcement learning, aiming to boost autonomous planning, tool use, and long‑horizon execution. Across five benchmarks—OfficeQA Pro, FinSearchComp, Finance Agent Benchmark, APEX‑Agents‑AA, and Workspace‑Bench‑Lite—the Navalia‑enhanced model shows consistent gains over the unmodified Qwen3.6‑35B‑A3B, demonstrating better evidence integration and numerical reasoning in financial analysis contexts.

## Key points

- Navalia creates multi‑step financial analysis tasks using verifiable evidence from corporate reports.
- Initialized from Qwen3.6-35B-A3B, Navalia outperforms the base model on five office‑task benchmarks.
- The framework combines independent LLM review, programmatic checks, SFT and RL to improve long‑horizon execution.

## Why it matters

Enhancing cowork agents’ ability to reliably synthesize evidence and execute complex financial reasoning can accelerate AI‑driven automation in enterprise analysis and broader office workflows.

## Sources

1. [Navalia: Advancing Cowork Agents through Verifiable Task Synthesis and Long-Horizon Post-Training](https://arxiv.org/abs/2610.26887) (arXiv cs.AI, 2026-10-21, primary source)

## Cite

Digest AI, "Navalia improves cowork agent performance over Qwen3.6-35B-A3B on finance benchmarks", 21 October 2026, https://digestai.news/story/navalia-improves-cowork-agent-performance-over-qwen3-6-35b-a3b-on-fina

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/navalia-improves-cowork-agent-performance-over-qwen3-6-35b-a3b-on-fina.json