Pith. sign in

REVIEW 9 cited by

Truncated Proximal Policy Optimization

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 2506.15050 v1 pith:DUAN2XXI submitted 2025-06-18 cs.AI

classification cs.AI
keywords policymodelsoptimizationt-ppoproximalreasoningtrainingtruncated
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, test-time scaling Large Language Models (LLMs) have demonstrated exceptional reasoning capabilities across scientific and professional tasks by generating long chains-of-thought (CoT). As a crucial component for developing these reasoning models, reinforcement learning (RL), exemplified by Proximal Policy Optimization (PPO) and its variants, allows models to learn through trial and error. However, PPO can be time-consuming due to its inherent on-policy nature, which is further exacerbated by increasing response lengths. In this work, we propose Truncated Proximal Policy Optimization (T-PPO), a novel extension to PPO that improves training efficiency by streamlining policy update and length-restricted response generation. T-PPO mitigates the issue of low hardware utilization, an inherent drawback of fully synchronized long-generation procedures, where resources often sit idle during the waiting periods for complete rollouts. Our contributions are two-folds. First, we propose Extended Generalized Advantage Estimation (EGAE) for advantage estimation derived from incomplete responses while maintaining the integrity of policy learning. Second, we devise a computationally optimized mechanism that allows for the independent optimization of the policy and value models. By selectively filtering prompt and truncated tokens, this mechanism reduces redundant computations and accelerates the training process without sacrificing convergence performance. We demonstrate the effectiveness and efficacy of T-PPO on AIME 2024 with a 32B base model. The experimental results show that T-PPO improves the training efficiency of reasoning LLMs by up to 2.5x and outperforms its existing competitors.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. Escaping the KL Agreement Trap in On-Policy Distillation

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    KAT detects persistent low-KL agreement traps in on-policy distillation via a dynamic threshold to filter weak supervision, improving avg@k by 2.66% and pass@k by 3.43% on four math benchmarks while shortening rollout...

  2. Explicit Critic Guidance for Aligning Diffusion Models

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Introduces a state-aligned latent actor-critic framework that lets diffusion models act as their own timestep-conditioned value functions for trajectory-level RL post-training and inference steering.

  3. Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    GenAC introduces generative critics with chain-of-thought reasoning and in-context conditioning to improve value approximation and downstream RL performance in LLMs compared to value-based and value-free baselines.

  4. Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    RAC is a closed-form bias correction for delayed rewards in RLHF that is unbiased under full mass reinjection of the delay kernel and reduces to V-trace with no delay.

  5. DynaResize: Runtime GPU Reallocation for Disaggregated LLM Post-Training

    cs.AI 2026-06 conditional novelty 6.0 of 10

    Dynamically reassigning GPUs between rollout and training during LLM post-training cuts pipeline bubbles, improving measured throughput by 66.5% over the best static split in the paper's 8-GPU test.

  6. Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.

  7. Trust Region On-Policy Distillation

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    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.

  8. Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

    cs.AI 2025-03 unverdicted novelty 5.0 of 10

    The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.

  9. A Survey of Reinforcement Learning for Large Reasoning Models

    cs.CL 2025-09 accept novelty 3.0 of 10

    A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.

Pith tools