Pith. sign in

REVIEW 19 cited by

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.05812 v3 pith:VKWBDRDN submitted 2025-04-08 cs.LG

Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

classification cs.LG
keywords reasoningourssupervisedaccuracybaseentropyfullyincentivization
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on external supervisions--such as labeled reasoning traces, verified golden answers, or pre-trained reward models. In this work, we propose Entropy Minimized Policy Optimization (\ours), which makes an early attempt at fully unsupervised LLM reasoning incentivization. By continuously minimizing the predictive entropy of LLMs on unlabeled questions in a latent semantic space, \ours achieves competitive performance compared to supervised counterparts on both mathematical and free-form natural reasoning tasks. Specifically, without any supervised signals, \ours boosts the accuracy of Qwen2.5-Math-7B Base from 30.7\% to 48.1\% on mathematical benchmarks and improves the accuracy of Qwen2.5-7B Base from 32.1\% to 50.1\% on MMLU-Pro. Primary experiments and analysis are also provided to interpret the effectiveness of \ours. Code is available at https://github.com/QingyangZhang/EMPO.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology

    cs.AI 2026-03 conditional novelty 8.0

    SARL rewards reasoning topology to improve label-free RL, outperforming baselines with gains up to 44.7% on math and 34.6% on open-ended tasks while maintaining more stable training.

  2. PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media

    cs.CL 2026-05 unverdicted novelty 7.0

    PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic onlin...

  3. Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning

    cs.AI 2026-05 unverdicted novelty 7.0

    GCPO uses team-level credit assignment via determinant volume over reward-weighted semantic embeddings to promote non-redundant correct reasoning paths, improving both accuracy and diversity in LLM training.

  4. Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning

    cs.AI 2026-05 unverdicted novelty 7.0

    GCPO shifts RLVR from rollout competition to team cooperation by assigning advantages via marginal contributions to a determinant-based coverage volume over semantic embeddings, yielding higher accuracy and solution d...

  5. Reinforcement Learning for Reasoning in Large Language Models with One Training Example

    cs.LG 2025-04 accept novelty 7.0

    One training example via RLVR boosts LLM math reasoning from 17.6% to 35.7% average across six benchmarks.

  6. Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models

    cs.CL 2026-06 unverdicted novelty 6.0

    PAPO improves reasoning performance in diffusion LLMs by converting sparse terminal rewards into dense step-wise credit and replaying real high-uncertainty trajectories, reporting gains up to 42.2% on Countdown.

  7. OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control

    cs.AI 2026-05 unverdicted novelty 6.0

    OracleTSC introduces a reward hurdle and uncertainty regularization to stabilize LLM-based reinforcement learning for traffic signal control, delivering 75% lower travel time and 67% lower queue length on benchmarks p...

  8. Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data

    cs.LG 2026-04 unverdicted novelty 6.0

    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.

  9. Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach

    cs.LG 2026-04 unverdicted novelty 6.0

    MedSSR improves LLM medical reasoning on rare diseases by up to 5.93% through knowledge-enhanced question synthesis and semi-supervised RL with self-generated pseudo-labels.

  10. ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision?

    cs.SE 2026-04 unverdicted novelty 6.0

    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.

  11. Can LLMs Learn to Reason Robustly under Noisy Supervision?

    cs.LG 2026-04 conditional novelty 6.0

    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 be...

  12. The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

    cs.LG 2025-05 unverdicted novelty 6.0

    Entropy minimization on self-generated outputs elicits strong reasoning in pretrained LLMs, matching or exceeding supervised RL methods on benchmarks.

  13. Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

    cs.CV 2026-07 accept novelty 5.0

    CTTA methods fall into optimization-based, parameter-efficient, and architecture-based families that adapt pretrained vision models online under continual unlabeled shifts while fighting forgetting and error accumulation.

  14. Trust Region On-Policy Distillation

    cs.LG 2026-05 unverdicted novelty 5.0

    TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.

  15. On the Generalization Gap in Self-Evolving Language Model Reasoning

    cs.CL 2026-05 unverdicted novelty 5.0

    Closed-loop self-evolution on LLMs improves reasoning on Knights and Knaves tasks but plateaus short of oracle-supervised levels, with multi-turn revision nearly matching it for large models.

  16. When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards

    cs.LG 2026-05 unverdicted novelty 5.0

    RLAVR uses the Corrective Advantage Gap metric and CARE policy to actively acquire ground-truth labels for key samples, stabilizing RLVR training and boosting performance with limited annotation budgets.

  17. Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization

    cs.LG 2026-05 unverdicted novelty 5.0

    Identifies two gaps in entropy-based uncertainty for LLM post-training and proposes GCPO to align geometry-aware disagreement measures with reward-based calibration for better gradient regulation.

  18. StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction

    cs.CL 2026-05 unverdicted novelty 5.0

    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.

  19. VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction

    cs.LG 2026-02 unverdicted novelty 5.0

    VI-CuRL stabilizes verifier-independent RL for LLM reasoning via confidence-guided curriculum that reduces action and problem variance, with a claimed proof of asymptotic unbiasedness and empirical gains over baselines.