A Reward-Guided Dual-Phase Framework for Adaptive Inference-Time Reasoning (2026.findings-acl)
Copied to clipboard
Yingqian Cui, Zhenwei Dai, Pengfei He, Bing He, Hui Liu, Zhan Shi, Xianfeng Tang, Jingying Zeng, Suhang Wang, Yue Xing, Jiliang Tang, Benoit Dumoulin
| Challenge: | Large Language Models (LLMs) have made strong progress in reasoning. |
| Approach: | They propose a dual-phase test-time scaling framework that separates planning and execution and performs search over each phase independently. |
| Outcome: | Experiments on math reasoning and code generation benchmarks show that the proposed approach improves accuracy while reducing redundant computation. |
Similar Papers
MetaScale: Test-Time Scaling with Evolving Meta-Thoughts (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches impose fixed cognitive structures that enhance performance in specific tasks but lack adaptability across diverse scenarios. |
| Approach: | They propose a test-time scaling framework based on meta-thoughts to improve performance . meta-thinkts are adaptive thinking strategies tailored to a given task . |
| Outcome: | Experimental results show that MetaScale outperforms standard inference approaches . it can scale more effectively with increasing sampling budgets and produces more structured responses . |
Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances on prompting and post-training have enabled LLMs to perform step-wise reasoning tasks, but they tend to explore unproductive solution paths without effective backtracking or strategy adjustment. |
| Approach: | They propose a framework that empowers LLMs to “think about how to think” and dynamically adapts reasoning strategies in real-time. |
| Outcome: | The proposed framework outperforms previous SOTA methods by 9-12% in accuracy while reducing inference time by 28-35% under the same compute budget. |
Reward-Guided Tree Search for Inference Time Alignment of Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Inference-time computation methods enhance performance of Large Language Models by leveraging additional computational resources. |
| Approach: | They propose an inference-time alignment method that leverages a reward model to achieve alignment through reward-guided tree search. |
| Outcome: | The proposed method outperforms other inference-time alignment methods on two benchmarks . it achieves comparable performance to preference-tuned models on both benchmarks, authors show . |
Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) increase test-time computation, often in the form of chain-of-thought (CoT) however, reasoning traces can become unnecessarily long, increasing computation costs without improving accuracy and sometimes even degrading performance. |
| Approach: | They propose a multi-stage efficient reasoning method that combines supervised fine-tuning with reinforcement learning using an adaptive length penalty. |
| Outcome: | The proposed method reduces response length by an average of 28% for 8B models and 40% for 32B models while incurring only minor performance drops of 1.6 and 2.5 points, respectively. |
SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have remarkable emergent abilities across various tasks, yet their performance on complex reasoning and planning tasks remains suboptimal. |
| Approach: | They propose a tree-search-based reasoning framework that encourages the exploration of intermediate steps and a round-scheduled strategy to manage draft model dispatching. |
| Outcome: | The proposed framework improves runtime speed and GPU memory management concurrently and handles multiple iterations for thought generation and state evaluation. |
Drift: Enhancing LLM Faithfulness in Rationale Generation via Dual-Reward Probabilistic Inference (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to improving LLM faithfulness rely on superficial calibration methods or costly retraining. |
| Approach: | They propose a probabilistic inference paradigm that leverages task-specific and lookahead rewards to ensure that LLM-generated rationales are more faithful to model decisions. |
| Outcome: | The proposed model improves both accuracy and faithfulness of Large Language Models (LLMs) on three reasoning tasks. |
Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence (2026.acl-long)
Copied to clipboard
| Challenge: | Guided by Gut (GG) is an efficient self-guided TTS framework for Large Language Models (LLMs) that performs step-by-step reasoning at a low cost without any reward models or verifiers. |
| Approach: | They propose a self-guided TTS framework that enables LLMs to perform step-by-step reasoning at a low cost without any reward models or verifiers. |
| Outcome: | Empirical evaluations show that GG performs better than TTS with PRMs while reducing GPU memory usage by up to 10. |
R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Qingfei Zhao, Ruobing Wang, Dingling Xu, Daren Zha, Ma Bowen, Zhichun Wang, Shijie Jia, Limin Liu, Xin Wang
| Challenge: | Large language models (LLMs) have demonstrated impressive capabilities in multi-step and long-chain reasoning, but extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge. |
| Approach: | They propose a framework for Reasoning–Search integration that integrates multi-reward signals to optimize the reasoning–search interaction trajectories. |
| Outcome: | Experiments on seven datasets show that R-Search significantly outperforms mainstream RAG baselines. |
Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have raised concerns regarding the hallucination and flaws in their reasoning process. |
| Approach: | They propose a framework to learn planning-based reasoning through Direct Preference Optimization on collected trajectories, which are ranked according to synthesized process rewards. |
| Outcome: | The proposed model surpasses GPT-3.5-Turbo on logical reasoning benchmarks on a set of logically-based reasoning tasks. |
Don’t Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls (2025.acl-long)
Copied to clipboard
Ante Wang, Linfeng Song, Ye Tian, Dian Yu, Haitao Mi, Xiangyu Duan, Zhaopeng Tu, Jinsong Su, Dong Yu
| Challenge: | Recent advances in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs), but at the cost of increased computational resources. |
| Approach: | They propose an e ffici ent tree sear ch framework that is a plug-and-play system compatible with various tree search algorithms. |
| Outcome: | The proposed framework reduces computational costs and prioritizes resource allocation to harder tasks (Levels 3-4) over simpler ones (Level 1-2), addressing both over-exploration in basic problems and under-exploation in complex cases. |