pith. sign in

arxiv: 2509.06948 · v3 · pith:HXQWBIZXnew · submitted 2025-09-08 · 💻 cs.CL

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning

classification 💻 cs.CL
keywords bridgereasoningtrainingrewardobjectivesoptimizationrewardsrlvr
0
0 comments X
read the original abstract

Supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) are two widely used post-training paradigms for improving the reasoning ability of large language models (LLMs). Recent methods attempt to integrate SFT and RLVR in a single stage by reweighting or scheduling their objectives. However, such coupling can be counterproductive because supervised updates are not uniformly beneficial for reward optimization. To address this, we propose BRIDGE, a scalable framework in which SFT learns to supervise RL by selectively transferring knowledge that improves reward optimization. Specifically, BRIDGE alternates two updates at each meta-training step: a base-model update that fuses the SFT and RL gradients, and an update to a lightweight low-rank adapter (LoRA) that coordinates the two objectives by maximizing a cooperative-gain signal, defined as the reward of joint SFT-RL training over an RL-only baseline. Across five mathematical reasoning benchmarks, BRIDGE consistently outperforms two-stage cold start, naive mixing, and representative single-stage integration baselines, yielding over three points average absolute improvement and more stable training dynamics. We further show that BRIDGE extends to logical reasoning and generalizes out-of-distribution to code and science without additional training, while staying robust under noisy rewards.

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 11 Pith papers

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

  1. Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation

    cs.LG 2026-04 unverdicted novelty 8.0

    Lightning OPD enforces teacher consistency by precomputing log-probabilities over SFT rollouts, matching standard OPD performance with bounded gradient discrepancy and achieving 4x speedup on math and code reasoning tasks.

  2. Learning Agentic Policy from Action Guidance

    cs.CL 2026-05 unverdicted novelty 7.0

    ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.

  3. Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level

    cs.LG 2026-05 unverdicted novelty 7.0

    AOPD modifies on-policy distillation by using localized divergence minimization for non-positive advantages instead of negative reinforcement, yielding average gains of 4.09/8.34 over standard OPD on math reasoning be...

  4. AIPO: Learning to Reason from Active Interaction

    cs.CL 2026-05 unverdicted novelty 6.0

    AIPO trains LLMs to expand their reasoning capability boundary via active multi-agent interaction with Verify, Knowledge, and Reasoning agents during RLVR, using importance sampling and clipping to handle feedback, th...

  5. AIPO: Learning to Reason from Active Interaction

    cs.CL 2026-05 unverdicted novelty 6.0

    AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.

  6. Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation

    cs.LG 2026-04 unverdicted novelty 6.0

    Lightning OPD is an offline on-policy distillation method that matches standard OPD performance at 4x efficiency by enforcing teacher consistency between SFT and distillation phases.

  7. MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?

    cs.LG 2026-02 unverdicted novelty 6.0

    MapTab benchmark shows current MLLMs struggle with multi-criteria multimodal route planning and that combining vision and language frequently underperforms single-modality approaches.

  8. MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?

    cs.LG 2026-02 conditional novelty 6.0

    MapTab is a new multimodal benchmark with 328 images and nearly 200k queries that shows current MLLMs have substantial difficulty with multi-criteria route planning when visual and tabular information must be combined.

  9. Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level

    cs.LG 2026-05 unverdicted novelty 5.0

    Asymmetric On-Policy Distillation replaces ineffective negative reinforcement with localized divergence minimization in low-advantage regions, yielding 4.09-8.34 point gains over standard OPD on math reasoning benchmarks.

  10. Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level

    cs.LG 2026-05 unverdicted novelty 5.0

    Asymmetric On-Policy Distillation improves on-policy distillation by using divergence minimization instead of negative reinforcement in low-advantage regions, yielding 4-8 point gains on math reasoning benchmarks whil...

  11. A Survey of Reinforcement Learning for Large Reasoning Models

    cs.CL 2025-09 accept novelty 3.0

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