AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation

Shaoxiong Yang, Junting Li, Mengyuan Zhang, Chao Li, Wei Liu, Jian Luan

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge editing in LLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add FutureMind planning to ToolCall agentQwen2.5-3B student · Multi-hop QA avg (4 benchmarks)ACC_E: 24.39 -> 32.16 (vs Search-o1)Improved
add FutureMind planningLlama3.1-8B · BamboogleACC_L: 52.00 -> 64.00 (vs Search-o1)Improved
use 3B model as teacher for 3B student (ablation)TC+FM · Multi-hop QA avg (4 benchmarks) (student Qwen2.5-3B)ACC_L: 29.49 -> 20.03Hurt
use 14B teacher instead of 72B teacher (ablation)TC+FM, Qwen2.5-7B student · Multi-hop QA avg (4 benchmarks)ACC_L: 44.38 -> 46.83Improved
add Strategy Planning module (ablation)FutureMind Qwen2.5-7B · Multi-hop QA avg (4 benchmarks)ACC_L: 40.33 -> 46.83Improved
add Problem Analysis module (ablation)FutureMind Qwen2.5-7B · Multi-hop QA avg (4 benchmarks)ACC_L: 43.84 -> 46.83Improved
add Logical Reasoning module (ablation)FutureMind Qwen2.5-7B · Multi-hop QA avg (4 benchmarks)ACC_L: 42.45 -> 46.83Improved
add Retrieval Guidance module (ablation)FutureMind Qwen2.5-7B · Multi-hop QA avg (4 benchmarks)ACC_L: 43.59 -> 46.83Improved
add Forward Stepwise strategy (ablation)FutureMind Qwen2.5-7B · Multi-hop QA avg (4 benchmarks)ACC_L: 42.79 -> 46.83Improved
add Backward Constraint strategy (ablation)FutureMind Qwen2.5-7B · Multi-hop QA avg (4 benchmarks)ACC_L: 44.67 -> 46.83Improved
add Parallel Intersection strategy (ablation)FutureMind Qwen2.5-7B · Multi-hop QA avg (4 benchmarks)ACC_L: 43.64 -> 46.83Improved
use Qwen2.5-72B teacher instead of Llama3.1-70B (ablation)TC+FM, Qwen2.5-72B student · Multi-hop QA avg (4 benchmarks)ACC_L: 55.68 -> 63.25Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy