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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations