SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
hub Canonical reference
R-Zero: Self-Evolving Reasoning LLM from Zero Data
Canonical reference. 71% of citing Pith papers cite this work as background.
47
Pith papers citing it
Background
71% of classified citations
abstract
Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models still rely heavily on vast human-curated tasks and labels, typically via fine-tuning or reinforcement learning, which poses a fundamental bottleneck to advancing AI systems toward capabilities beyond human intelligence. To overcome this limitation, we introduce R-Zero, a fully autonomous framework that generates its own training data from scratch. Starting from a single base LLM, R-Zero initializes two independent models with distinct roles, a Challenger and a Solver. These models are optimized separately and co-evolve through interaction: the Challenger is rewarded for proposing tasks near the edge of the Solver capability, and the Solver is rewarded for solving increasingly challenging tasks posed by the Challenger. This process yields a targeted, self-improving curriculum without any pre-existing tasks and labels. Empirically, R-Zero substantially improves reasoning capability across different backbone LLMs, e.g., boosting the Qwen3-4B-Base by +6.49 on math-reasoning benchmarks and +7.54 on general-domain reasoning benchmarks.
hub tools
citation-role summary
background 11
method 2
baseline 1
citation-polarity summary
representative citing papers
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
TTRL-CoCoV is a confidence-conditioned test-time RL framework that selectively applies verification to address pseudo-label errors and diversity collapse, yielding +9.8% Pass@1 and +18.7% Pass@16 gains over prior TTRL on reasoning benchmarks.
EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
A proposer-solver agent pair achieves supervised-level video temporal grounding and fine-grained captioning from 2.5K unlabeled videos via self-reinforcing evolution.
QueST adapts LLMs at test time by generating query-specific problem-solution pairs for self-supervised fine-tuning, improving reasoning performance without external data.
COSPLAY co-evolves an LLM decision agent with a skill bank agent to improve long-horizon game performance, reporting over 25.1% average reward gains versus frontier LLM baselines on single-player benchmarks.
SPIRAL is a closed-loop think-act-reflect framework using PlanAgent, VideoGenerator, and CriticAgent plus GRPO self-evolution to improve long-horizon action-conditioned video generation, with new dataset and benchmark showing gains over open-loop baselines.
IFCodeEvolve synthesizes coding data via actor-schema co-evolution with MCTS, boosting a 32B model's performance to match proprietary SOTA on instruction following.
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.
BenchEvolver evolves coding problem solutions to generate harder, valid tasks, producing LiveCodeBench-Plus where frontier models score 27.5-62.6% and enabling RL gains on held-out tests.
SEAL co-evolves LLM agents and environments via shared turn-level failure diagnoses, yielding +8.25 to +26.25 point gains on tool-use tasks with only 400 samples.
EVE-Agent adds an evidence verifier to the proposer-solver loop that rewards spans by marginal accuracy gain, producing self-generated but inspectable training examples for search agents.
EvoVid proposes a temporal-centric self-evolution framework for Video-LLMs that uses temporal-aware Questioner and temporal-grounded Solver rewards to improve performance directly from unannotated videos.
PopuLoRA shows that co-evolving populations of LoRA adapters through cross-evaluated self-play can outperform compute-matched single-agent baselines on multiple code and math reasoning benchmarks.
Video-Zero is an annotation-free Questioner-Solver co-evolution framework that centers self-evolution on temporally localized evidence to improve video VLMs.
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.
A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.
MORA breaks the safety-helpfulness ceiling in LLMs by pre-sampling single-reward prompts and rewriting them to incorporate multi-dimensional intents, delivering 5-12.4% gains in sequential alignment and 4.6% overall improvement in simultaneous alignment.
Seirênes trains LLMs via adversarial self-play to generate and overcome evolving distractions, producing gains of 7-10 points on math reasoning benchmarks and exposing blind spots in larger models.
Preping builds agent memory via proposer-guided synthetic practice and selective validation, matching offline/online methods at 2-3x lower deployment cost.
G-Zero uses the Hint-δ intrinsic reward to drive co-evolution between a Proposer and Generator via GRPO and DPO, providing a theoretical suboptimality guarantee for self-improvement from internal dynamics alone.
SEIF creates a self-reinforcing loop in which an LLM alternately generates increasingly difficult instructions and learns to follow them better using reinforcement learning signals from its own judgments.
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
citing papers explorer
-
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
MORA breaks the safety-helpfulness ceiling in LLMs by pre-sampling single-reward prompts and rewriting them to incorporate multi-dimensional intents, delivering 5-12.4% gains in sequential alignment and 4.6% overall improvement in simultaneous alignment.
-
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
A parameter-free sampling strategy called CUTS combined with Mixed-CUTS training prevents mode collapse in RL for saturated LLM reasoning tasks and raises AIME25 Pass@1 accuracy by up to 15.1% over standard GRPO.