Views
No views yet
👉 There's a newer, better model: RefinedToolCall-V5-3B
An on-policy self-RFT successor that improves multi-turn agentic ~3.7× plus single-turn calling (0.707) and error-recovery (0.896) — with reasoning intact. Try it:ollama run refinedneuro/refinedtoolcallv5-3b
WeiboAI/VibeThinker-3B
(Qwen2-based) that adds Hermes-style function calling (<think>…</think> +
<tool_call>…</tool_call>) and — new in v0.4 — meaningfully better multi-turn agentic tool use,
while preserving its math/STEM reasoning.multi_turn tasks — executed against the real stateful backends for genuine tool responses, with a
planning <think> and an explicit turn-termination step — multi-turn success improved ~2.5–3×
with no regression to reasoning, recovery, or single-turn calling:| metric | v0.3 | v0.4 | Δ |
|---|---|---|---|
BFCL multi_turn (held-out multi_turn_base, n=47, k=3) | ~0.06 | 0.156 avg / 0.213 pass@3 | ▲ ~2.5–3× |
| BFCL single-turn FC (held-out, n=167) | 0.647 | 0.659 | ▲ |
| Recovery from tool errors (held-out glm, n=250) | 0.888 | 0.884 | ≈ |
| AIME-2024 pass@4 | 0.933 | 0.933 | = |
| AIME-2024 avg@4 | 0.783 | 0.838 | ▲ |
multi_turn with the official
multi_turn_checker (compares final backend state + responses + invoke order) — far stronger
than single-turn AST matching. v0.3 baseline here was only 6.4%.ls -la instead of
calling the provided cd/touch/...), never terminated a turn, and didn't plan call sequences.<think> and a terminating reply (teaching the model to stop and yield).long_context and miss_param categories at up to 24k tokens.
This data+context scale-up was the single biggest lever (0.128 → 0.234).<|im_end|>. The model emits a <think> plan, then one or more <tool_call> blocks, then a final
natural-language reply per turn.multi_turn_base): long, open-ended agent loops remain brittle (occasional buggy generated code,
imperfect long-horizon planning). Strong at single-turn function calling and math reasoning; not
production-ready for fully autonomous multi-step agentic work.