Towards Inference-time Scaling for Continuous Space Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in reasoning large language models have expanded along training and inferencetime dimensions. |
| Approach: | They propose to use COCONUT (CITATION) continuous space reasoning LM as the backbone to generate diverse reasoning paths through dropout-based sampling. |
| Outcome: | The proposed method could enable performance gains similar to those observed in the discrete space, but only marginally improves in the continuous space. |
Similar Papers
A Comprehensive Survey of Process Reward Models: Data Generation, Model Construction, and Usage (2026.acl-long)
Copied to clipboard
Congmin Zheng, Jiachen Zhu, Zhuoying Ou, Yuxiang Chen, Kangning Zhang, Rong Shan, Zeyu Zheng, Mengyue Yang, Jianghao Lin, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have advanced reasoning ability, yet conventional alignment remains dominated by outcome reward models that judge only final answers. |
| Approach: | They summarize applications across math, code, text, multimodal reasoning, robotics, and agents . goal is to clarify design spaces, reveal open challenges, and guide future research toward fine-grained, robust reasoning alignment. |
| Outcome: | The proposed model enables finer credit assignment, richer diagnostics, and improved robustness. |
Logical Reasoning with Outcome Reward Models for Test-Time Scaling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), but it is under-explored in deductive reasoning. |
| Approach: | They propose to use Chain-of-Thought to generate data using single and multiple samples to train ORMs. |
| Outcome: | The proposed model expands the type of errors covered in the training dataset, covering previously unexplored error types. |
When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models have shifted focus toward scaling inference-time compute. |
| Approach: | They propose to scale inference-time compute in a multilingual, multi-task setting . they propose to use m-ArenaHard-v2.0 prompts to sample multiple outputs in parallel . |
| Outcome: | The proposed solutions achieve an average +6.8 jump in win-rates for 8B models on m-ArenaHard-v2.0 prompts in non-English languages against proprietary models like Gemini. |
Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLM-based recommenders lack explicit modeling of geographic signals . without explicit modeling geographic signals, recommenders struggle to capture core mobility patterns . |
| Approach: | They propose a framework that utilizes geography as a decision variable within the reasoning process. |
| Outcome: | The proposed framework achieves over 10% relative gains in hit rate over strongest LLM-based baselines and improves cross-city transfer. |
Scaling Evaluation-Time Compute with Reasoning Models as Evaluators (2026.findings-acl)
Copied to clipboard
Seungone Kim, Ian Wu, Jinu Lee, Xiang Yue, Seongyun Lee, Minkyeong Moon, Carolin Lawrence, Kiril Gashteovski, Julia Hockenmaier, Graham Neubig, Sean Welleck
| Challenge: | Language model (LM) evaluators that generate chain-of-thought reasoning are widely used for the assessment of LM responses. |
| Approach: | They investigate whether increasing LMs' "thinking" time through scaling test-time compute can improve an LM's evaluation capability. |
| Outcome: | The proposed reasoning models improve evaluation performance monotonically with the number of reasoning tokens generated, mirroring trends seen in LM reasoning. |
SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing training pipelines sample training examples uniformly across steps or epochs, ignoring differences in difficulty, redundancy, and learning value, which slows learning and wastes computation. |
| Approach: | They propose a self-paced learning framework that enables efficient learning based on the capability of the model being trained through optimizing which data to use and when. |
| Outcome: | The proposed framework achieves comparable or better accuracy than state-of-the-art baselines while using up to (100 times) fewer samples. |
Continuous Context Sampling Allows Extending Diversity Boundaries of Large Language Models (2026.acl-srw)
Copied to clipboard
| Challenge: | Large language models exhibit a persistent limitation: repeated generations from the same prompt tend to be semantically similar. |
| Approach: | They propose to construct a conditioning distribution from a small set of diverse anchor generations and use it to condition an LLM's generation distribution. |
| Outcome: | The proposed framework significantly expands the model's reachable semantic range by constructing a conditioning distribution from a small set of diverse anchor generations. |
R-PRM: Reasoning-Driven Process Reward Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing Process Reward Models (PRMs) output evaluation scores directly, limiting both learning efficiency and evaluation accuracy. |
| Approach: | They propose a Reasoning-Driven Process Reward Modeling (R-PRM) which activates inherent reasoning to enhance process-level evaluation. |
| Outcome: | The proposed model outperforms baseline models on ProcessBench and PRMBench by 13.9 and 8.5 F1 scores. |
From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has recently advanced the reasoning capabilities of large language models (LLMs). |
| Approach: | They propose a method that incorporates partial solution prefixes from expert demonstrations to guide the policy. |
| Outcome: | The proposed methods outperform strong baselines, yielding faster convergence and a higher performance ceiling. |
ReEfBench: Quantifying the Reasoning Efficiency of LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Chain-of-Thought evaluations do not distinguish between genuine reasoning and mere verbosity. |
| Approach: | They propose a framework for the non-intrusive, comprehensive process-centric evaluation of reasoning grounded in First-Order Logic. |
| Outcome: | The proposed framework identifies four distinct behavioral prototypes and diagnoses the failure modes. |