Learning Adaptive Parallel Reasoning with Language Models
- URL: http://arxiv.org/abs/2504.15466v1
- Date: Mon, 21 Apr 2025 22:29:02 GMT
- Title: Learning Adaptive Parallel Reasoning with Language Models
- Authors: Jiayi Pan, Xiuyu Li, Long Lian, Charlie Snell, Yifei Zhou, Adam Yala, Trevor Darrell, Kurt Keutzer, Alane Suhr,
- Abstract summary: We propose Adaptive Parallel Reasoning (APR), a novel reasoning framework that enables language models to orchestrate both serialized and parallel computations end-to-end.<n> APR generalizes existing reasoning methods by enabling adaptive multi-threaded inference using spawn() and join() operations.<n>A key innovation is our end-to-end reinforcement learning strategy, optimizing both parent and child inference threads to enhance task success rate without requiring predefined reasoning structures.
- Score: 70.1745752819628
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs, leading to increased latency and exhausted context windows, while parallel methods such as self-consistency suffer from insufficient coordination, resulting in redundant computations and limited performance gains. To address these shortcomings, we propose Adaptive Parallel Reasoning (APR), a novel reasoning framework that enables language models to orchestrate both serialized and parallel computations end-to-end. APR generalizes existing reasoning methods by enabling adaptive multi-threaded inference using spawn() and join() operations. A key innovation is our end-to-end reinforcement learning strategy, optimizing both parent and child inference threads to enhance task success rate without requiring predefined reasoning structures. Experiments on the Countdown reasoning task demonstrate significant benefits of APR: (1) higher performance within the same context window (83.4% vs. 60.0% at 4k context); (2) superior scalability with increased computation (80.1% vs. 66.6% at 20k total tokens); (3) improved accuracy at equivalent latency (75.2% vs. 57.3% at approximately 5,000ms). APR represents a step towards enabling language models to autonomously optimize their reasoning processes through adaptive allocation of computation.
Related papers
- DeltaLLM: A Training-Free Framework Exploiting Temporal Sparsity for Efficient Edge LLM Inference [19.987309147268586]
We present DeltaLLM, a training-free framework that exploits temporal sparsity in attention patterns to enable efficient LLM inference on resource-constrained edge devices.<n>We evaluate our framework on the edge-device-friendly BitNet-b1.58-2B-4T model and Llama3.2-1B-Instruct model across diverse language tasks.
arXiv Detail & Related papers (2025-07-25T18:23:18Z) - Scaling Linear Attention with Sparse State Expansion [58.161410995744596]
Transformer architecture struggles with long-context scenarios due to quadratic computation and linear memory growth.<n>We introduce a row-sparse update formulation for linear attention by conceptualizing state updating as information classification.<n>Second, we present Sparse State Expansion (SSE) within the sparse framework, which expands the contextual state into multiple partitions.
arXiv Detail & Related papers (2025-07-22T13:27:31Z) - ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation [53.149817480019834]
Recent advancements in large reasoning models (LRMs) have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length by Chain-of-Thought (CoT)<n>We propose a framework dubbed ConciseHint, which continuously encourages the reasoning model to speak concisely by injecting the textual hint during the token generation of the reasoning process.<n>Experiments on the state-of-the-art LRMs, including DeepSeek-R1 and Qwen-3 series, demonstrate that our method can effectively produce concise reasoning processes while maintaining performance well.
arXiv Detail & Related papers (2025-06-23T16:20:44Z) - Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
arXiv Detail & Related papers (2025-06-05T07:31:18Z) - Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models [68.96619605651155]
Large reasoning models (LRMs) may drastically increase the output length due to overthinking.<n>We propose a dynamic optimization framework that segments model-generated reasoning paths into distinct thinking patterns.<n>Our method achieves up to a 12% accuracy improvement and reducing token usage from approximately 5,000 to 3,000 tokens.
arXiv Detail & Related papers (2025-05-27T20:59:29Z) - EquiBench: Benchmarking Code Reasoning Capabilities of Large Language Models via Equivalence Checking [54.354203142828084]
We present the task of equivalence checking as a new way to evaluate the code reasoning abilities of large language models.<n>We introduce EquiBench, a dataset of 2400 program pairs spanning four programming languages and six equivalence categories.<n>Our evaluation of 17 state-of-the-art LLMs shows that OpenAI o3-mini achieves the highest overall accuracy of 78.0%.
arXiv Detail & Related papers (2025-02-18T02:54:25Z) - Entropy Adaptive Decoding: Dynamic Model Switching for Efficient Inference [0.0]
We present Entropy Adaptive Decoding (EAD), a novel approach for efficient language model inference.<n>EAD switches between different-sized models based on prediction uncertainty.<n>We show remarkable efficiency gains across different model families.
arXiv Detail & Related papers (2025-02-05T22:15:21Z) - Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving [0.0]
Recent advances in large language models (LLMs) have predominantly focused on maximizing accuracy and reasoning capabilities.<n>This paper investigates the potential synergy between reasoning enhancement and computational efficiency by analyzing the integration of two contrasting approaches.
arXiv Detail & Related papers (2024-12-20T08:42:45Z) - The Surprising Effectiveness of Test-Time Training for Few-Shot Learning [59.309477460893916]
Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks.<n>We investigate the effectiveness of test-time training (TTT) as a mechanism for improving LMs' reasoning and few-shot learning capabilities.<n>Our findings highlight the limitations of in-context learning for novel tasks and demonstrate the potential of test-time training to enhance language model adaptability.
arXiv Detail & Related papers (2024-11-11T18:59:45Z) - COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks.
We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges.
Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
arXiv Detail & Related papers (2024-10-12T23:56:19Z) - Think Beyond Size: Adaptive Prompting for More Effective Reasoning [0.0]
We introduce Adaptive Prompting, a dynamic and iterative framework designed to enhance reasoning by incorporating real-time adjustments to prompt structures and validation mechanisms.<n>Results demonstrate that Adaptive Prompting significantly improves performance on diverse reasoning benchmarks, including arithmetic reasoning (GSM8K, MultiArithm), logical reasoning and commonsense tasks.<n>Our approach enables smaller models to achieve competitive performance with larger counterparts, such as GPT-4, while maintaining computational efficiency.
arXiv Detail & Related papers (2024-10-10T17:14:36Z) - ISO: Overlap of Computation and Communication within Seqenence For LLM Inference [8.616769297336708]
This paper introduces a novel strategy for computation-communication overlap that operates at the sequence level.
Experimental evaluations conducted using 30b/70b models have demonstrated significant improvements in efficiency.
arXiv Detail & Related papers (2024-09-04T05:22:17Z) - Building Math Agents with Multi-Turn Iterative Preference Learning [56.71330214021884]
This paper studies the complementary direct preference learning approach to further improve model performance.<n>Existing direct preference learning algorithms are originally designed for the single-turn chat task.<n>We introduce a multi-turn direct preference learning framework, tailored for this context.
arXiv Detail & Related papers (2024-09-04T02:41:04Z) - Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning.
Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
arXiv Detail & Related papers (2024-04-02T16:25:30Z) - Listen Attentively, and Spell Once: Whole Sentence Generation via a
Non-Autoregressive Architecture for Low-Latency Speech Recognition [66.47000813920619]
We propose a non-autoregressive end-to-end speech recognition system called LASO.
Because of the non-autoregressive property, LASO predicts a textual token in the sequence without the dependence on other tokens.
We conduct experiments on publicly available Chinese dataset AISHELL-1.
arXiv Detail & Related papers (2020-05-11T04:45:02Z)
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.