Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:RAR2PEP2record.jsonopen to challenge →
read the original abstract
In-context learning (ICL) enables large language models (LLMs) to perform downstream tasks through advanced prompting and high-quality demonstrations. However, traditional ICL paradigms encounter significant limitations in complex reasoning tasks, stemming primarily from their dependence on example quality and absence of explicit reasoning guidance. To address these challenges, we introduce HiAR-ICL, a **Hi**gh-level **A**utomated **R**easoning paradigm in **ICL** that shifts focus from specific examples to abstract reasoning patterns, thereby extending the conventional concept of "context" in ICL. Our approach begins by defining five atomic reasoning actions, upon which we employ Monte Carlo Tree Search to systematically construct high-level reasoning patterns. During inference, HiAR-ICL dynamically selects appropriate reasoning patterns based on problem attributes, providing explicit guidance for the model's reasoning process. Experiments demonstrate HiAR-ICL's effectiveness and efficiency: utilizing only 200 prior samples with Qwen2.5-7B-Instruct, our method achieves 80.6% accuracy on MATH and 62.5% on AMC, exceeding GPT-4o's 77.2% and 57.5%. Our approach enhances performance across models of varying sizes while generalizing effectively across domains. Further analysis reveals that HiAR-ICL can also serve as a plug-and-play inference method compatible with post-training techniques like GRPO. Code and data are available at https://github.com/jinyangwu/HiARICL.
This paper has not been read by Pith yet.
Forward citations
Cited by 11 Pith papers
-
ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices
ProactiveMobile is a new benchmark for proactive mobile agents that tests latent intent inference from context and executable API generation, where a fine-tuned 7B model reaches 19.15% success versus 15.71% for o1 and...
-
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
Maestro uses outcome-based RL to train a lightweight policy that orchestrates ensembles of frozen expert models and skills, reporting 70.1% average accuracy across ten multimodal benchmarks and outperforming GPT-5 and...
-
Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
IH-GRPO introduces implicit hierarchical control via a surrogate loss to decouple tool invocation from execution in LLMs, reporting 1.87-2.53% gains on math reasoning benchmarks.
-
Decoupled Travel Planning with Behavior Forest
Behavior Forest decouples multi-constraint travel planning into parallel behavior trees with LLM nodes and global coordination, yielding 6.67% and 11.82% gains over prior methods on two benchmarks.
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
-
Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models
Meta-Reasoner applies contextual multi-armed bandits to adaptively select LLM reasoning strategies at inference time, reporting 9-12% accuracy gains and 28-35% time reductions on math and science benchmarks.
-
MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
MILES dynamically expands step-wise memory with learnable selection heads that rerank candidates and guide reasoning, improving LLM test-time performance under limited supervision.
-
Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation
DPVR-LF routes saturated vision tokens into a one-layer side branch after layer 4, runs text-only processing through layers 5-17, and performs late fusion at the final layer to reduce visual computation while preservi...
-
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
OPID distills episode- and step-level skills from completed on-policy trajectories, routes them via critical-first mechanism, and combines the resulting log-probability shift advantage with outcome advantage for polic...
-
Improving Multimodal Reasoning via Worst Dimension Optimization
Proposes Worst Dimension Optimization to address equal-weighting limitations in Process Reward Models for multimodal reasoning.
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.