LBR performs token-level test-time scaling via local branch routing on hidden states, enabling end-to-end RL training and improving Pass@1 and Pass@32 on math benchmarks over CoT and RLVR baselines.
hub
Soft thinking: Unlocking the reasoning potential of llms in continuous concept space
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
UniVLR unifies textual and visual reasoning in multimodal LLMs by compressing reasoning traces and auxiliary images into visual latent tokens for direct inference without interleaved text CoT.
Abstract-CoT lets models reason with short discrete latent token sequences from a reserved vocabulary, using warm-up training and RL to match verbal CoT performance with up to 11.6x fewer tokens.
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
Dropout-GRPO uses structured dropout to generate trajectory variance for GRPO in latent-reasoning models like Coconut, raising GSM8K pass@1 from 27.29% to 29.01%.
GRAM is a latent-variable generative model that performs recursive reasoning via stochastic trajectories, trained with amortized variational inference to support multi-hypothesis reasoning and unconditional generation.
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.
Terminator learns to predict optimal early-exit points in chain-of-thought reasoning by training on the first positions where the model emits its final answer, yielding 14-55% shorter outputs with no accuracy loss.
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
HAB applies coarse-to-fine budgeting to LLM reasoning, predicting per-problem depth and learning intra-step token budgets via PPL comparisons and adaptive Pareto optimization, yielding higher accuracy and lower token use than standard CoT on GSM8K and MATH500.
LEPO applies RL to continuous latent representations in LLMs by injecting Gumbel-Softmax stochasticity for diverse trajectory sampling and unified gradient estimation, outperforming existing discrete and latent RL methods.
Reason-IAD improves explainable industrial anomaly detection by combining retrieval-augmented category knowledge with entropy-guided latent reasoning and dynamic visual patch injection in MLLMs.
Latent-CURE introduces latent-space chain-of-thought reasoning and dual-asymmetric optimization to produce transparent, robust breast cancer diagnoses in imbalanced cohorts.
citing papers explorer
-
Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.