RiVER applies calibrated ranking rewards from execution scores to train LLMs on score-based tasks without ground-truth, producing gains on both heuristic contests and exact-solution coding benchmarks.
Rlve: Scaling up reinforcement learning for language models with adaptive verifiable environments.arXivpreprint
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
abstract
We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language models (LMs). RLVE enables each verifiable environment to dynamically adapt its problem difficulty distribution to the policy model's capabilities as training progresses. In contrast, static data distributions often lead to vanishing learning signals when problems are either too easy or too hard for the policy. To implement RLVE, we create RLVE-Gym, a large-scale suite of 400 verifiable environments carefully developed through manual environment engineering. Using RLVE-Gym, we show that environment scaling, i.e., expanding the collection of training environments, consistently improves generalizable reasoning capabilities. RLVE with joint training across all 400 environments in RLVE-Gym yields a 3.37% absolute average improvement across six reasoning benchmarks, starting from one of the strongest 1.5B reasoning LMs. By comparison, continuing this LM's original RL training yields only a 0.49% average absolute gain despite using over 3x more compute. We release our code publicly.
years
2026 11representative citing papers
EvoTrainer co-evolves LLM policies and training harnesses via empirical feedback to match or exceed human-engineered RL on math reasoning, code generation, and long-horizon software engineering.
TRON supplies 520 rule-verifiable online visual reasoning environments across five ability buckets that generate unlimited training instances for RL post-training, yielding consistent gains on ten external multimodal benchmarks for three vision-language models.
EvoEnv lets a single policy synthesize, validate, and use Python environments with durable solve-verify asymmetry to improve reasoning performance on Qwen3-4B-Thinking from 72.4 to 74.8 while fixed-data baselines decline.
ShapeCodeBench introduces a renewable benchmark for perception-to-program reconstruction of synthetic shapes, with evaluations showing low exact-match performance from current models and heuristics.
ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.
SCALER creates adaptive synthetic environments for RL-based LLM reasoning training that outperforms fixed-dataset baselines with more stable long-term progress.
Gym-V supplies 179 visual environments showing that observation scaffolding like captions and rules matters more for training success than the choice of RL algorithm.
ZONOS2 8B is a scaled MoE TTS model with 900M active parameters trained on 6M hours of data that reports competitive SOTA results on naturalness, speaker similarity, WER, and a new ZTTS1-Eval benchmark while releasing weights and code.
DocArena automates creation of multimodal document QA training data via MLLM-based structuring and cross-page reasoning pairs, yielding agents with top retrieval and QA performance in unified tests.
S^3-R1 generates synthetic multi-hop questions and uses combined intermediate and final rewards to train RL models for retrieval and answering, reporting up to 10% better out-of-domain generalization.
citing papers explorer
-
Reinforcement Learning without Ground-Truth Solutions can Improve LLMs
RiVER applies calibrated ranking rewards from execution scores to train LLMs on score-based tasks without ground-truth, producing gains on both heuristic contests and exact-solution coding benchmarks.
-
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
EvoTrainer co-evolves LLM policies and training harnesses via empirical feedback to match or exceed human-engineered RL on math reasoning, code generation, and long-horizon software engineering.
-
TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL
TRON supplies 520 rule-verifiable online visual reasoning environments across five ability buckets that generate unlimited training instances for RL post-training, yielding consistent gains on ten external multimodal benchmarks for three vision-language models.
-
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
EvoEnv lets a single policy synthesize, validate, and use Python environments with durable solve-verify asymmetry to improve reasoning performance on Qwen3-4B-Thinking from 72.4 to 74.8 while fixed-data baselines decline.
-
ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes
ShapeCodeBench introduces a renewable benchmark for perception-to-program reconstruction of synthetic shapes, with evaluations showing low exact-match performance from current models and heuristics.
-
ZAYA1-8B Technical Report
ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.
-
SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning
SCALER creates adaptive synthetic environments for RL-based LLM reasoning training that outperforms fixed-dataset baselines with more stable long-term progress.
-
Gym-V: A Unified Vision Environment System for Agentic Vision Research
Gym-V supplies 179 visual environments showing that observation scaffolding like captions and rules matters more for training success than the choice of RL algorithm.
-
ZONOS2 Technical Report
ZONOS2 8B is a scaled MoE TTS model with 900M active parameters trained on 6M hours of data that reports competitive SOTA results on naturalness, speaker similarity, WER, and a new ZTTS1-Eval benchmark while releasing weights and code.
-
DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents
DocArena automates creation of multimodal document QA training data via MLLM-based structuring and cross-page reasoning pairs, yielding agents with top retrieval and QA performance in unified tests.
-
$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data
S^3-R1 generates synthetic multi-hop questions and uses combined intermediate and final rewards to train RL models for retrieval and answering, reporting up to 10% better out-of-domain generalization.