No article text was recorded for this version.
self-supervised process supervision
Version 1 of 175 papers97 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
- Blog: Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
- Blog: Maximizing Confidence Alone Improves Reasoning
- Blog: Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models
- Blog: Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
- Blog: Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
- Blog: Intrinsic Credit Assignment for Long Horizon Interaction
- Blog: Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning
- Blog: Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
- Blog: Bertmucb: An Efficient Approach for Sentiment Analysis
- Blog: DuPO: Enabling Reliable Self-Verification via Dual Preference Optimization
- Blog: Reinforced Question Rewriting for Conversational Question Answering
- Blog: Learning to Reason without External Rewards
- Blog: Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
- Blog: Learning to Reason for Long-Form Story Generation
- Blog: Free Process Rewards without Process Labels
- Blog: TreeRL: LLM Reinforcement Learning with On-Policy Tree Search
- Blog: DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning
- Blog: Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
- Blog: Intra-Trajectory Consistency for Reward Modeling
- Blog: On Learning to Think with Action Process Reward Models
- Blog: CellDuality: Unlocking Biological Reasoning in LLMs with Self-Supervised RLVR
- Blog: Reinforcing General Reasoning without Verifiers
- Blog: Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
- Blog: Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
- Blog: Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNets
- Blog: Teacher Forcing Recovers Reward Functions for Text Generation
- Blog: Rectifying LLM Thought from Lens of Optimization
- Blog: ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
- Blog: Test-Time Scaling with Reflective Generative Model
- Blog: Reinforced Question Rewriting for Conversational Question Answering
- Blog: IRIS: Intrinsic Reward Image Synthesis
- Blog: CaTS: Calibrated Test-Time Scaling for Efficient LLM Reasoning
- Blog: SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins
- Blog: Coupled Variational Reinforcement Learning for Language Model General Reasoning
- Blog: Learn How to See: Collaborative Embodied Learning for Object Detection and Camera Adjusting
- Blog: Efficient Test-Time Scaling via Self-Calibration
- Blog: Reward-based Input Construction for Cross-document Relation Extraction
- Blog: Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
- Blog: Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models
- Blog: Confidence as a Reward: Transforming LLMs into Reward Models
- Blog: Why is Your Language Model a Poor Implicit Reward Model?
- Blog: QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
- Blog: AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
- Blog: IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
- Blog: VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism
- Blog: Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNets
- Blog: Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning
- Blog: Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models
- Blog: Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning
- Blog: Unlocking Anticipatory Text Generation: A Constrained Approach for Faithful Decoding with Large Language Models
- Blog: Improving Language Model Reasoning with Self-motivated Learning
- Blog: Reinforcing Multimodal Understanding and Generation with Dual Self-rewards
- Blog: Self-Improvement in Language Models: The Sharpening Mechanism
- Blog: Reasoning with Sampling: Your Base Model is Smarter Than You Think
- Blog: PACR: Progressively Ascending Confidence Reward for LLM Reasoning
- Blog: Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo
- Blog: Anchor-Final Self-Supervision Drives Hallucination-Aware Optimization in Large Vision-Language Models
- Blog: TTRL: Test-Time Reinforcement Learning
- Blog: Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning
Showing 60 of 75 papers.
History & citation
Current · Permanent link
- This direction split from Reinforcement Learning from Internal Confidence Signals (56% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_self_supervised_process_supervision_325c64de,
title = {self-supervised process supervision},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/self-supervised-process-supervision/rdr_325c64de60014380b41db74e21b4514d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_self_supervised_process_supervision_325c64de_v1,
title = {self-supervised process supervision},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/self-supervised-process-supervision/rdr_325c64de60014380b41db74e21b4514d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}