Cross-Agent Learning Signals Enable Coordinated Role-Decomposed LLM Training
cs.LG, cs.AI
Submitted: 2026-06-09
Updated: 2026-10-07
Code: https://github.com/StonyBrookNLP/ircot
Terminology
Sources
- Learning to Give Checkable Answers with Prover-Verifier Games
- Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
- Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search
- An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents
- Prover-Verifier Games improve legibility of LLM outputs
- Tongyi DeepResearch Technical Report
- SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
- TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks