Challenge: Existing methods for self-improvement of large language models with verifiable rewards (RLVR) can drift over iterations, while corpus-grounded approaches rely on curated data environments.
Approach: They propose a Web-grounded Iterative Self-play Tree framework for domain-targeted reasoning improvement that learns directly from the open-web without requiring any pre-arranged domain corpus.
Outcome: The proposed framework outperforms both purely endogenous self-evolution and corpus-grounded self-play baselines and is domain-steerable.

Similar Papers

UR2 : Unify RAG and Reasoning through Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Existing attempts to unify large language models are limited to open-domain QA with fixed retrieval settings.
Approach: They propose a general reinforcement learning framework that dynamically coordinates retrieval and reasoning.
Outcome: The proposed framework outperforms existing paradigms on open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks.
TreeRL: LLM Reinforcement Learning with On-Policy Tree Search (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for On-Policy LLM RL typically train a separate process reward model, which suffers from distribution mismatch and reward hacking.
Approach: They propose a reinforcement learning framework that directly incorporates on-policy tree search for RL training.
Outcome: Experiments on math and code reasoning benchmarks show that tree search achieves superior performance compared to traditional ChainRL.
Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains (2026.acl-long)

Copied to clipboard

Challenge: Reinforcement learning with verifiable rewards (RLVR) has been effective on structured tasks, but its reliance on simple, rule-based verifiers creates a bottleneck.
Approach: They propose a framework that uses a generative verifier to provide soft, probabilistic rewards.
Outcome: The proposed framework outperforms existing models up to 10x their size and can be scalable and effective.
S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to incentivize LLMs’ deep thinking abilities require large-scale data or significant training efforts.
Approach: They introduce an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.
Outcome: The proposed framework outperforms models trained on long-CoT distilled data with 3.1k initialization samples and achieves an accuracy improvement of 51.0% to 81.6%.
Reasoning-Guided Exploration for Online DPO (2026.findings-acl)

Copied to clipboard

Challenge: Recent work has aimed to enhance reasoning capabilities of language models, but these methods are limited to domains with objectively verifiable answers.
Approach: They propose a self-play framework to improve reasoning on general-domain data.
Outcome: Experiments show that the proposed framework improves reasoning performance on general-domain data while maintaining competitive performance on verifiable academic benchmarks.
TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing RL methods rely on unstructured self-sampling to fit scalar rewards, resulting in inefficient rollouts.
Approach: They propose a structured template-guided RL framework that augments policy optimization with explicit template guidance.
Outcome: Experiments show that TemplateRL outperforms GRPO and GRPI by 99% on AIME and 41% on AMC with superior stability on weak models and remarkable cross-domain generalization.
OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing RLHF frameworks face inference bottlenecks and complexity barriers restricting their accessibility for newcomers.
Approach: They propose an open-source RLHF framework that can be used to train large language models.
Outcome: The proposed framework achieves superior training efficiency with speedups ranging from 1.22 to 1.68 across different model sizes compared to state-of-the-art frameworks, while requiring significantly fewer lines of code for implementation.
Reflect, Rewrite, Repeat: How Simple Arithmetic Enables Advanced Reasoning in Small Language Models (2026.findings-eacl)

Copied to clipboard

Challenge: Recent advances in language model reasoning require computationally intensive reinforcement learning and massive datasets.
Approach: They propose a framework that combines Direct Preference Optimization and Supervised Fine-Tuning with selective guidance from larger models and iteratively refining solutions through a "reflect, rewrite, repeat" cycle.
Outcome: The proposed framework shows significant performance improvements across arithmetic, symbolic and cognitive reasoning benchmarks.
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning for LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to reinforcement learning with verifiable reward (RLVR) are limited by difficulty or lack of exploration.
Approach: They propose a self-evolving curriculum learning framework based on chain-of-thought reasoning optimization that constrains exploration space by self-generating and verifying CoT trajectories.
Outcome: The proposed framework enables LLMs to solve previously unsolved problems without external supervision and is compatible with various RL fine-tuning methods.
RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services (2026.acl-industry)

Copied to clipboard

Challenge: Social networking services (SNS) are critical infrastructure for global interaction . supervised fine-tuning (SFT) can improve in-domain performance, but it often induces a ”seesaw” trade-off with out-of-domain robustness .
Approach: They propose an SNS-oriented LLM with a progressive, RL-prioritized post-training paradigm for fast and stable adaptation.
Outcome: The proposed model improves over the previous 7B model by 2.41 on average . it also yields an 8.74 average gain over its Qwen3-4B base .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations