No article text was recorded for this version.
sparse reward bottleneck
Version 1 of 192 papers104 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Compositional Skill Acquisition in Agentic Pipelines via Reinforcement Learning and Knowledge Distillation
- Blog: ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
- Blog: CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization
- Blog: Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
- Blog: MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models
- Blog: Learning to Reason under Off-Policy Guidance
- Blog: Generalization of RLVR Using Causal Reasoning as a Testbed
- Blog: Nudging the Boundaries of LLM Reasoning
- Blog: What Can You Do When You Have Zero Rewards During RL?
- Blog: Leanabell-Prover-V2: Verifier-integrated Reasoning for Formal Theorem Proving via Reinforcement Learning
- Blog: SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
- Blog: Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
- Blog: Empowering Small VLMs to Think with Dynamic Memorization and Exploration
- Blog: Wiki-R1: Incentivizing Multimodal Reasoning for Knowledge-based VQA via Data and Sampling Curriculum
- Blog: Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning
- Blog: SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning
- Blog: Softened Symbol Grounding for Neuro-symbolic Systems
- Blog: InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning
- Blog: UFT: Unifying Supervised and Reinforcement Fine-Tuning
- Blog: Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
- Blog: HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness
- Blog: DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models
- Blog: Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation
- Blog: P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads
- Blog: Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models
- Blog: Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
- Blog: DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage
- Blog: Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions
- Blog: Leanabell-Prover: Posttraining Scaling in Formal Reasoning
- Blog: ScRPO: From Errors to Insights
- Blog: Provable Sample Efficiency of Curriculum Post-Training for Transformer Reasoning
- Blog: WARM: A Weakly (+Semi) Supervised Math Word Problem Solver
- Blog: A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
- Blog: MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
- Blog: Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
- Blog: Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models
- Blog: Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference
- Blog: Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
- Blog: Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision
- Blog: AgentFly: Extensible and Scalable Reinforcement Learning for LM Agents
- Blog: One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL
- Blog: Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
- Blog: HyperTree Proof Search for Neural Theorem Proving
- Blog: From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Training Retrieval-Augmented Generation Agents
- Blog: STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving
- Blog: Representation-Based Exploration for Language Models: From Test-Time to Post-Training
- Blog: $\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving
- Blog: Generalization of RLVR Using Causal Reasoning as a Testbed
- Blog: AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems
- Blog: Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasoner
- Blog: SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
- Blog: A Critical Evaluation of AI Feedback for Aligning Large Language Models
- Blog: Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
- Blog: MME-Reasoning: A Broad-Spectrum Benchmark for Evaluating Logical Reasoning in MLLMs
- Blog: Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
- Blog: Learn Hard Problems During RL with Reference Guided Fine-tuning
- Blog: Contrastive Reinforcement Learning of Symbolic Reasoning Domains
- Blog: Training Chain-of-Thought via Latent-Variable Inference
- Blog: OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
- Blog: Stress-Testing Capability Elicitation With Password-Locked Models
Showing 60 of 92 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_sparse_reward_bottleneck_1b0fc216,
title = {sparse reward bottleneck},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sparse-reward-bottleneck/rdr_1b0fc216406944378839a14498969c34},
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_sparse_reward_bottleneck_1b0fc216_v1,
title = {sparse reward bottleneck},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sparse-reward-bottleneck/rdr_1b0fc216406944378839a14498969c34/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}