Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation
cs.CL
Submitted: 2026-08-31
Updated: 2026-08-31
Code: https://github.com/jiny1623/taiscore
Terminology
Sources
- Training Verifiers to Solve Math Word Problems
- DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research
- Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- Holistic Evaluation of Language Models
- OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
- R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning
- Language Models Can Learn from Verbal Feedback Without Scalar Rewards
- HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
- Training Language Models with Language Feedback at Scale
- DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Reverse-Engineered Reasoning for Open-Ended Generation
- RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks
- Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning
- Qwen3 Technical Report
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering