Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

• URL: http://arxiv.org/abs/2503.01307v1
• Date: Mon, 03 Mar 2025 08:46:22 GMT
• Title: Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
• Authors: Kanishk Gandhi, Ayush Chakravarthy, Anikait Singh, Nathan Lile, Noah D. Goodman,
• Abstract summary: Reinforcement learning can drive self-improvement in language models on verifiable tasks.<n>We find that Qwen-2.5-3B far exceeds Llama-3.2-3B under identical RL training for the game of Countdown.<n>Our study reveals that Qwen naturally exhibits these reasoning behaviors, whereas Llama initially lacks them.
• Score: 28.565225092457897
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time inference has emerged as a powerful paradigm for enabling language models to ``think'' longer and more carefully about complex challenges, much like skilled human experts. While reinforcement learning (RL) can drive self-improvement in language models on verifiable tasks, some models exhibit substantial gains while others quickly plateau. For instance, we find that Qwen-2.5-3B far exceeds Llama-3.2-3B under identical RL training for the game of Countdown. This discrepancy raises a critical question: what intrinsic properties enable effective self-improvement? We introduce a framework to investigate this question by analyzing four key cognitive behaviors -- verification, backtracking, subgoal setting, and backward chaining -- that both expert human problem solvers and successful language models employ. Our study reveals that Qwen naturally exhibits these reasoning behaviors, whereas Llama initially lacks them. In systematic experimentation with controlled behavioral datasets, we find that priming Llama with examples containing these reasoning behaviors enables substantial improvements during RL, matching or exceeding Qwen's performance. Importantly, the presence of reasoning behaviors, rather than correctness of answers, proves to be the critical factor -- models primed with incorrect solutions containing proper reasoning patterns achieve comparable performance to those trained on correct solutions. Finally, leveraging continued pretraining with OpenWebMath data, filtered to amplify reasoning behaviors, enables the Llama model to match Qwen's self-improvement trajectory. Our findings establish a fundamental relationship between initial reasoning behaviors and the capacity for improvement, explaining why some language models effectively utilize additional computation while others plateau.

Related papers

• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.190800043449336]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance. We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)
• Rethinking Reflection in Pre-Training [13.372316326688722]
  A language model's ability to reflect on its own reasoning provides a key advantage for solving complex problems. We introduce deliberate errors into chains-of-thought and test whether the model can still arrive at the correct answer by recognizing and correcting these mistakes. By tracking performance across different stages of pre-training, we observe that this self-correcting ability appears early and improves steadily over time.
  arXiv  Detail & Related papers  (2025-04-05T02:24:07Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs) We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization. OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [54.04678363287392]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)
• Unveiling Reasoning Thresholds in Language Models: Scaling, Fine-Tuning, and Interpretability through Attention Maps [3.8936716676293917]
  This study investigates the in-context learning capabilities of various decoder-only transformer-based language models with different model sizes and training data.<n>We identify a critical parameter threshold (1.6 billion), beyond which reasoning performance improves significantly in tasks such as commonsense reasoning in multiple-choice question answering and deductive reasoning.
  arXiv  Detail & Related papers  (2025-02-21T00:48:32Z)
• Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation [18.826857684901118]
  We introduce a causal-temporal modeling framework consisting of two stages.<n>The first stage endows the model with causal-temporal modeling ability by introducing two self-supervision auxiliary tasks.<n>In the second stage, we argue that not all feature tokens contribute equally to pose estimation.<n>Our method outperforms state-of-the-art methods on three large-scale benchmark datasets.
  arXiv  Detail & Related papers  (2025-01-24T09:45:16Z)
• Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm [9.577716124021029]
  We argue that GPT 3.5's declining performance on 2-back and 3-back tasks reflects a working memory capacity limit similar to humans.<n>By analyzing a range of open-source language models of varying performance levels on these tasks, we show that the poor performance instead reflects a limitation in task comprehension and task set maintenance.
  arXiv  Detail & Related papers  (2024-12-24T03:06:52Z)
• Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision [120.40788744292739]
  We propose a two-player paradigm that separates the roles of reasoning and critique models. We first propose AutoMathCritique, an automated and scalable framework for collecting critique data. We demonstrate that the critique models consistently improve the actor's performance on difficult queries at test-time.
  arXiv  Detail & Related papers  (2024-11-25T17:11:54Z)
• Improving Language Model Reasoning with Self-motivated Learning [60.779625789039486]
  textitSelf-motivated Learning framework motivates the model itself to automatically generate rationales on existing datasets. We train a reward model with the rank to evaluate the quality of rationales, and improve the performance of reasoning through reinforcement learning.
  arXiv  Detail & Related papers  (2024-04-10T14:05:44Z)
• R-Tuning: Instructing Large Language Models to Say `I Don't Know' [66.11375475253007]
  Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. Previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. We present a new approach called Refusal-Aware Instruction Tuning (R-Tuning) Experimental results demonstrate R-Tuning effectively improves a model's ability to answer known questions and refrain from answering unknown questions.
  arXiv  Detail & Related papers  (2023-11-16T08:45:44Z)
• Does Self-Rationalization Improve Robustness to Spurious Correlations? [19.553357015260687]
  We ask whether training models to self-rationalize can aid in their learning to solve tasks for the right reasons. We evaluate robustness to spurious correlations in fine-tuned encoder-decoder and decoder-only models of six different sizes. We find that while self-rationalization can improve robustness to spurious correlations in low-resource settings, it tends to hurt robustness in higher-resource settings.
  arXiv  Detail & Related papers  (2022-10-24T19:54:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.