No article text was recorded for this version.
sparse reward signals
Version 1 of 143 papers49 conceptsfrozen 2026-10-04
Papers in this version
- Blog: NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation
- Blog: Execution-based Code Generation using Deep Reinforcement Learning
- Blog: Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
- Blog: Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
- Blog: CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design
- Blog: PRM-PBE: Process Reward Model for Reinforcement Learning in Programming-by-Example
- Blog: SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications
- Blog: Tuning Models of Code with Compiler-Generated Reinforcement Learning Feedback
- Blog: MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?
- Blog: Beyond Scalar Rewards: Dense Feedback for LLM Policy Synthesis in Sequential Social Dilemmas
- Blog: Process Supervision-Guided Policy Optimization for Code Generation
- Blog: Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
- Blog: Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs
- Blog: Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs
- Blog: Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
- Blog: Unsupervised program synthesis for images by sampling without replacement
- Blog: Multi-Turn Code Generation Through Single-Step Rewards
- Blog: WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning
- Blog: Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions
- Blog: Deep Reinforcement Learning from Hierarchical Preference Design
- Blog: StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback
- Blog: SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning
- Blog: Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards
- Blog: QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation
- Blog: RL with Learnable Textual Feedback: A Bilevel Approach
- Blog: Lean2Isabelle: Factorized Cross-Assistant Proof Translation
- Blog: IRCoCo: Immediate Rewards-Guided Deep Reinforcement Learning for Code Completion
- Blog: RiskPO: Risk-based Policy Optimization with Verifiable Reward for LLM Post-Training
- Blog: Predicate-Guided Generation for Mathematical Reasoning
- Blog: SWE-RM: Execution-free Feedback for Software Engineering Agents
- Blog: Learning a Meta-Solver for Syntax-Guided Program Synthesis
- Blog: RLTF: Reinforcement Learning from Unit Test Feedback
- Blog: Matching Decompilation as a Verifier-Guided Task for Human-Centered Coding Agents
- Blog: BOOSTAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
- Blog: CodePRM: Execution Feedback-enhanced Process Reward Model for Code Generation
- Blog: STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models
- Blog: From Search to Policy: Thompson Sampling Trees for Robust LLM Code Refinement
- Blog: TritonRL: Training LLMs to Think and Code Triton Without Cheating
- Blog: On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding
- Blog: Learning to Generate Structured Output with Schema Reinforcement Learning
- Blog: Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
- Blog: Process-Verified Reinforcement Learning for Theorem Proving via Lean
- Blog: Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
History & citation
Current · Permanent link
- This direction split from Dense Rewards for Neural Program Synthesis (58% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_sparse_reward_signals_fbd12965,
title = {sparse reward signals},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sparse-reward-signals/rdr_fbd1296522f541ea921d13ad5e262612},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_sparse_reward_signals_fbd12965_v1,
title = {sparse reward signals},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sparse-reward-signals/rdr_fbd1296522f541ea921d13ad5e262612/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}