ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search
- URL: http://arxiv.org/abs/2504.10893v1
- Date: Tue, 15 Apr 2025 06:06:50 GMT
- Title: ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search
- Authors: Yize Zhang, Tianshu Wang, Sirui Chen, Kun Wang, Xingyu Zeng, Hongyu Lin, Xianpei Han, Le Sun, Chaochao Lu,
- Abstract summary: We introduce ARise, a novel framework that integrates risk assessment of intermediate reasoning states with dynamic retrieval--augmented generation (RAG)<n>ARise significantly outperforms the state-of-the-art KAR methods by up to 23.10%, and the latest RAG-equipped large reasoning models by up to 25.37%.
- Score: 46.7782420285593
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models (LLMs) have demonstrated impressive capabilities and are receiving increasing attention to enhance their reasoning through scaling test--time compute. However, their application in open--ended, knowledge--intensive, complex reasoning scenarios is still limited. Reasoning--oriented methods struggle to generalize to open--ended scenarios due to implicit assumptions of complete world knowledge. Meanwhile, knowledge--augmented reasoning (KAR) methods fail to address two core challenges: 1) error propagation, where errors in early steps cascade through the chain, and 2) verification bottleneck, where the explore--exploit tradeoff arises in multi--branch decision processes. To overcome these limitations, we introduce ARise, a novel framework that integrates risk assessment of intermediate reasoning states with dynamic retrieval--augmented generation (RAG) within a Monte Carlo tree search paradigm. This approach enables effective construction and optimization of reasoning plans across multiple maintained hypothesis branches. Experimental results show that ARise significantly outperforms the state--of--the--art KAR methods by up to 23.10%, and the latest RAG-equipped large reasoning models by up to 25.37%.
Related papers
- Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
arXiv Detail & Related papers (2025-07-13T03:29:41Z) - Lost at the Beginning of Reasoning [82.18834329384514]
We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.<n>We introduce a new benchmark specifically constructed with deliberately flawed first reasoning steps to systematically evaluate model self-correction capabilities.
arXiv Detail & Related papers (2025-06-27T09:53:57Z) - LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization [30.95342819013663]
Large language models (LLMs) have demonstrated impressive capabilities in reasoning.<n>Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL) approaches.<n>We propose Learning to Think-and-Search (LeTS), a novel framework that hybridizes stepwise process reward and outcome-based reward to current RL methods for RAG.
arXiv Detail & Related papers (2025-05-23T04:04:05Z) - a1: Steep Test-time Scaling Law via Environment Augmented Generation [45.19240207975418]
Environment Augmented Generation (EAG) is a framework that enhances large language models' reasoning through real-time environmental feedback.
EAG enables deliberate backtracking and strategic replanning through tight integration of execution feedback and branching exploration.
A1-32B model achieves state-of-the-art performance among similar-sized models across all benchmarks.
arXiv Detail & Related papers (2025-04-20T12:55:59Z) - ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation [38.64751082999587]
Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy.<n>We propose ReaRAG, a factuality-enhanced reasoning model that explores diverse queries without excessive iterations.<n>Our study enhances LRMs' factuality while effectively integrating robust reasoning for Retrieval-Augmented Generation (RAG)
arXiv Detail & Related papers (2025-03-27T17:44:18Z) - A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond [88.5807076505261]
Large Reasoning Models (LRMs) have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference.<n>A growing concern lies in their tendency to produce excessively long reasoning traces.<n>This inefficiency introduces significant challenges for training, inference, and real-world deployment.
arXiv Detail & Related papers (2025-03-27T15:36:30Z) - Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [54.04678363287392]
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.<n>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) - DeepRAG: Thinking to Retrieve Step by Step for Large Language Models [92.87532210660456]
We propose DeepRAG, a framework that models retrieval-augmented reasoning as a Markov Decision Process (MDP)<n>By iteratively decomposing queries, DeepRAG dynamically determines whether to retrieve external knowledge or rely on parametric reasoning at each step.<n> Experiments show that DeepRAG improves retrieval efficiency and boosts answer accuracy by 26.4%, demonstrating its effectiveness in enhancing retrieval-augmented reasoning.
arXiv Detail & Related papers (2025-02-03T08:22:45Z) - Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems [92.89673285398521]
o1-like reasoning systems have demonstrated remarkable capabilities in solving complex reasoning tasks.<n>We introduce an imitate, explore, and self-improve'' framework to train the reasoning model.<n>Our approach achieves competitive performance compared to industry-level reasoning systems.
arXiv Detail & Related papers (2024-12-12T16:20:36Z) - A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentation [0.0]
Advancements in image segmentation play an integral role within the broad scope of Deep Learning-based Computer Vision.<n>Uncertainty quantification has been extensively studied within this context, enabling the expression of model ignorance (epistemic uncertainty) or data ambiguity (aleatoric uncertainty) to prevent uninformed decision-making.
arXiv Detail & Related papers (2024-11-25T13:26:09Z) - Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework [77.45983464131977]
We focus on how likely it is that a RAG model's prediction is incorrect, resulting in uncontrollable risks in real-world applications.<n>Our research identifies two critical latent factors affecting RAG's confidence in its predictions.<n>We develop a counterfactual prompting framework that induces the models to alter these factors and analyzes the effect on their answers.
arXiv Detail & Related papers (2024-09-24T14:52:14Z) - Rethinking State Disentanglement in Causal Reinforcement Learning [78.12976579620165]
Causality provides rigorous theoretical support for ensuring that the underlying states can be uniquely recovered through identifiability.
We revisit this research line and find that incorporating RL-specific context can reduce unnecessary assumptions in previous identifiability analyses for latent states.
We propose a novel approach for general partially observable Markov Decision Processes (POMDPs) by replacing the complicated structural constraints in previous methods with two simple constraints for transition and reward preservation.
arXiv Detail & Related papers (2024-08-24T06:49:13Z) - MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
arXiv Detail & Related papers (2024-06-20T03:50:23Z) - Towards Trustworthy Explanation: On Causal Rationalization [9.48539398357156]
We propose a new model of rationalization based on two causal desiderata, non-spuriousness and efficiency.
The superior performance of the proposed causal rationalization is demonstrated on real-world review and medical datasets.
arXiv Detail & Related papers (2023-06-25T03:34:06Z) - Causal Intervention-based Prompt Debiasing for Event Argument Extraction [19.057467535856485]
We compare two kinds of prompts, name-based prompt and ontology-base prompt, and reveal how ontology-base prompt methods exceed its counterpart in zero-shot event argument extraction (EAE)
Experiments on two benchmarks demonstrate that modified by our debias method, the baseline model becomes both more effective and robust, with significant improvement in the resistance to adversarial attacks.
arXiv Detail & Related papers (2022-10-04T12:32:00Z)
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.