Ahmed Zeer, Osama Shbib, Muzaffer Kaan Yuce, Himmet Toprak Kesgin, Mehmet Fatih Amasyali
原文摘要
We improve Turkish mathematical reasoning in Large Language Models by combining LoRA fine-tuning, weight-space model merging, and search-based inference. Using Turkish-Llama 8B-DPO with Turkish translations of MetaMath, NuminaMath, and TigerLab, we find data quality beats scale (Mix-30k best among fine-tuned; large MetaMath underperforms). Linear merging delivers the largest gains (GSM8K up to 0.63), while Ties is modest and Breadcrumbs/Slerp degrade. Search with MCTS and Tree of Thoughts improves mean LLM-judge scores for reasoning quality on a 0-100 scale. Limitations include machine translation, limited scale, and search stochasticity.
Ahmed Zeer, Osama Shbib, Muzaffer Kaan Yuce, Himmet Toprak Kesgin, Mehmet Fatih Amasyali
原文摘要
Search allows a robotic policy to evaluate candidate futures before committing to an action. Motivated by test-time planning for vision-language action (VLA) models, we study selective search over action chunks in PushT using a frozen Action Chunking with Transformers (ACT) policy. Beam search generates perturbed alternatives around the policy prediction and scores them through rollouts from cloned simulator states. Across 50 evaluation episodes, beam search raises task success from 0% to 18% and increases average cumulative reward from 39.44 to 103.2. We introduce One Step Ahead (OSA), a gate that simulates the nominal policy chunk and invokes full search only when its predicted coverage drop exceeds a threshold. In the reported ablations, OSA preserves or improves success while reducing runtime by approximately 3x relative to full beam search. Ablations over tree depth, branching factor, beam width, and replanning frequency show that larger search budgets do not consistently improve performance. The results support selective test-time search for action-chunking policies; evaluation on language-conditioned VLAs and physical robots remains future work.