arXiv AI

Diversity Combining for Multi-Path LLM Reasoning

The paper treats multi‑path large language model reasoning as a diversity‑combining problem, analogous to noisy channel observations in wireless communications. It shows that the optimal symmetric linear combiner of latent embeddings is uniform, justifying majority vote in standard self‑consistency while allowing for weighting or pruning when prompt‑template branches are heterogeneous. By reducing path correlation through prompt‑template diversity, the authors propose an Adaptive‑K rule that selects an optimal number of reasoning paths, preserving most of the accuracy achieved with a fixed large number of paths across multiple models and benchmarks.

arXiv AI

Sep 12

When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making

The paper introduces Bayesian backward reasoning as a label‑free anchor for multi‑agent collective decision‑making. By constructing reverse posteriors from explicit likelihoods, the authors obtain differently factorized approximations of the underlying posterior, reducing shared errors among agents. Using Jensen‑Shannon divergence to rank agents, they propose three aggregation strategies—hard selection (MinJS), soft reweighting (FwdJS), and log‑linear fusion (LogLin)—which consistently outperform baseline methods on the DDXPlus benchmark across five LLM backbones, especially when agents disagree.

By Ken Chen, Wei Wang, Sachith Seneviratne, Hansani Weeratunge, Saman Halgamuge

llms agents

arXiv AI

Aug 11

Test-Time Augmentation for LLMs: When Input Diversity Beats Output Diversity at Matched Compute

arXiv:2608. 09351v1 Announce Type: cross Abstract: Test-time scaling improves LLM accuracy but multiplies inference cost, making the accuracy gained per unit of compute the metric that matters in deployment.

By Nikita Kozodoi, Zainab Afolabi, Jack Butler

llms nlp multimodal

arXiv AI

Aug 7

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

arXiv:2608. 05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity.

By Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Lena Trigg, Ali Subhan, Muhammad Ali, Dean F. Hougen

llms reinforcement-learning

arXiv Machine Learning

Sep 23

Confidence Composition for Multiagent Language Model Systems

The paper addresses the lack of system‑level confidence estimates in multiagent language model systems such as collaborative reasoning and debate. It introduces confidence composition methods, including confidence‑aware routing and log‑odds pooling, to combine agent confidences while maintaining selective utility and probabilistic reliability. Experiments on five benchmarks with diverse model pairs show that gated‑fusion techniques improve AUARC and Brier scores compared to single‑agent and standard debate baselines, and a shared dependence discount further enhances reliability.

By Ali Elahi, Michael J. Curry, Barbara Di Eugenio

llms agents benchmarks

arXiv AI

Jul 13

HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs

arXiv:2604. 20140v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks.

By Darsh Kachroo, Arjun Prasaath Anbazhagan, Adriana Caraeni, Brennan Lagasse, Kevin Zhu

llms agents reinforcement-learning fine-tuning benchmarks

arXiv Computation and Language

6d ago

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

arXiv:2606.29985v2 Announce Type: replace Abstract: Diversity in LLM mathematical reasoning is critical for exploration, but common diversity metrics mostly capture surface-level variation rather tha...

By Sangmook Lee, Minbeom Kim, Jeonghye Kim, Dohyung Kim, Sojeong Rhee, Kyomin Jung

llms

Hugging Face Trending Papers

Jun 29

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

Diversity in LLM mathematical reasoning is critical for exploration, but common diversity metrics mostly capture surface-level variation rather than differences in how a problem is solved. We address this gap by introducing approach-level diversity: variation in strategies across correct solutions to the same problem.

llms

arXiv AI

Jun 10

Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning

arXiv:2606. 10184v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) relies on the diversity of $K$ rollouts within each group; otherwise, the group-mean advantage $A^{(k)} = r^{(k)} - \mu_r$ collapses to zero.

By Wooil Jung

llms reinforcement-learning

arXiv AI

Aug 3

Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling

arXiv:2605. 15100v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning.

By Rongman Xu, Yifei Li, Tianzhe Zhao, Yanrui Wu, Bo Li, Hang Yan

llms efficiency benchmarks safety

arXiv AI

Jun 3

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

arXiv:2605. 30789v2 Announce Type: replace-cross Abstract: We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs.

By Yiming Ren, Yiran Xu, Zicheng Lin, Chufan Shi, Yukang Chen, Dingdong Wang, Tianhe Wu, Junjie Wang, Yujiu Yang, Yu Qiao, Ruihang Chu

llms benchmarks

arXiv AI

Jul 10

Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework

arXiv:2607. 08017v1 Announce Type: cross Abstract: Large-Language Models (LLMs) can be prone to flawed and unfaithful reasoning that decoding strategies like Self-Consistency (SC) fail to detect as they evaluate only final-answer agreement while ignoring the logical validity of intermediate steps.

By Riccardo Revalor, Jalees Rehman, Debjit Pal

llms benchmarks safety

arXiv Machine Learning

Jul 31

Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation

arXiv:2607. 27783v1 Announce Type: cross Abstract: Large Language Models (LLMs) explore problems through chain-of-thought, but this exploration is buried in unstructured prose.

By Amruta Parulekar, Jinu Lee, Dilek Hakkani-T\"ur, Hari Sundaram

llms benchmarks

Related stories