# DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning

arXiv: https://arxiv.org/abs/2410.20215 · HTML: https://mlsanity.com/paper/2410.20215/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 26 Oct 2024.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training](https://mlsanity.com/paper/2309.17179/) (2023)
- [Compositional Exemplars for In-context Learning](https://mlsanity.com/paper/2302.05698/) (2023)
- [Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations](https://mlsanity.com/paper/2205.12685/) (2022)
- [Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning](https://mlsanity.com/paper/2406.14283/) (2024)
- [How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse](https://mlsanity.com/paper/2404.05090/) (2024)
- [Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment](https://mlsanity.com/paper/2305.05940/) (2023)
- [Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations](https://mlsanity.com/paper/2212.09865/) (2022)
- [Calibrating the Confidence of Large Language Models by Eliciting Fidelity](https://mlsanity.com/paper/2404.02655/) (2024)
- [Consent in Crisis: The Rapid Decline of the AI Data Commons](https://mlsanity.com/paper/2407.14933/) (2024)
- [Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations](https://mlsanity.com/paper/2305.15035/) (2023)
- [Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks](https://mlsanity.com/paper/2405.10548/) (2024)
- [Demonstration Augmentation for Zero-shot In-context Learning](https://mlsanity.com/paper/2406.01224/) (2024)
- [Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning](https://mlsanity.com/paper/2406.14022/) (2024)

## Built on by (most cited first, 6 of 6)

- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking](https://mlsanity.com/paper/2501.01306/) (2025)
- [LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation](https://mlsanity.com/paper/2502.07365/) (2025)
- [MetaScale: Test-Time Scaling with Evolving Meta-Thoughts](https://mlsanity.com/paper/2503.13447/) (2025)
- [Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding](https://mlsanity.com/paper/2504.01281/) (2025)
- [Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.11995/) (2025)

## Abstract (arXiv)

Zero-shot in-context learning (ZS-ICL) aims to conduct in-context learning (ICL) without using human-annotated demonstrations. Most ZS-ICL methods use large language models (LLMs) to generate (input, label) pairs as pseudo-demonstrations and leverage historical pseudo-demonstrations to help solve the current problem. They assume that problems are from the same task and traverse them in a random order. However, in real-world scenarios, problems usually come from diverse tasks, and only a few belong to the same task. The random traversing order may generate unreliable pseudo-demonstrations and lead to error accumulation. To address this problem, we reformulate ZS-ICL as a planning problem and propose a Demonstration-aware Monte Carlo Tree Search (MCTS) approach (DAWN-ICL), which leverages MCTS to strategically plan the problem-solving trajectories for ZS-ICL. In addition, to achieve effective and efficient Q value estimation, we propose a novel demonstration-aware Q-value function and use it to enhance the selection phase and accelerate the expansion and simulation phases in MCTS. Extensive experiments demonstrate the effectiveness and efficiency of DAWN-ICL on in-domain and cross-domain scenarios, and it even outperforms ICL using human-annotated labels. The code is available at https://github.com/RUCAIBox/MCTS4ZSICL.