BRRL derives an analytic optimal policy for regularized constrained RL that guarantees monotonic improvement and yields the BPO algorithm that matches or exceeds PPO.
hub
TTRL: Test-time reinforcement learning
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
representative citing papers
A model trained only by proposing and solving its own verifiable code tasks achieves state-of-the-art results on math and coding benchmarks without external data.
MLS-Bench shows that current AI agents fall short of reliably inventing generalizable ML methods, with engineering tuning easier than genuine invention.
Mutual Reinforcement Learning allows heterogeneous LLMs to exchange experience through mechanisms like Peer Rollout Pooling, Cross-Policy GRPO Advantage Sharing, and Success-Gated Transfer, with outcome-level sharing identified as favorable on the stability-support trade-off.
GXPO approximates longer local lookahead in GRPO training via gradient extrapolation from two optimizer steps using three backward passes total, improving pass@1 accuracy by 1.65-5.00 points over GRPO and delivering up to 4x step speedup.
A training recipe for tool-integrated reasoning models achieves state-of-the-art open-source results on math benchmarks such as 96.7% and 99.2% on AIME 2025 at 4B and 30B scales by balancing tool-use trajectories and optimizing for pass@k during SFT before stable RLVR.
DDRL reduces spurious reward noise in test-time RL for math by excluding ambiguous samples, using fixed advantages, and adding consensus-based updates, outperforming prior TTRL methods on math benchmarks.
ProactAgent learns a proactive retrieval policy via reinforcement learning on paired task continuations, improving lifelong agent performance and cutting retrieval overhead on SciWorld, AlfWorld, and StuLife.
TEMPO scales test-time training for large reasoning models by interleaving policy refinement on unlabeled data with critic recalibration on labeled data via an EM formulation, yielding large gains on AIME tasks.
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.
Recovering an orthogonal basis from model activations yields a model-native skill characterization that improves reasoning Pass@1 by up to 41% via targeted data selection and supports inference steering, outperforming human-characterized alternatives.
MARS² integrates multi-agent collaboration with tree-structured search in RL to boost code generation by increasing exploratory diversity and using path-level group advantages for credit assignment.
ZeroCoder co-evolves coder and tester LLMs via self-generated code-test execution feedback to improve code generation up to 21.6% without ground-truth supervision.
Online Label Refinement lets LLMs learn robust reasoning from noisy supervision by correcting labels when majority answers show rising rollout success and stable history, delivering 3-4% gains on math and reasoning benchmarks even at high noise levels.
GrandCode is the first AI system to consistently beat all human participants and place first in live Codeforces competitive programming contests.
PACEvolve++ uses a phase-adaptive reinforcement learning advisor to decouple hypothesis selection from execution in LLM-driven evolutionary search, delivering faster convergence than prior frameworks on load balancing, recommendation, and protein tasks.
StraTA improves LLM agent success rates to 93.1% on ALFWorld and 84.2% on WebShop by sampling a compact initial strategy and training it jointly with action execution via hierarchical GRPO-style rollouts.
TCER corrects triviality bias in endogenous rewards for text generation by rewarding relative information gain modulated by probability correction, yielding consistent unsupervised improvements on writing benchmarks and transferring to math reasoning.
FREIA applies free energy principles and adaptive advantage shaping to unsupervised RL, outperforming baselines by 0.5-3.5 Pass@1 points on math reasoning with a 1.5B model.
citing papers explorer
-
ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision?
ZeroCoder co-evolves coder and tester LLMs via self-generated code-test execution feedback to improve code generation up to 21.6% without ground-truth supervision.