Pith. sign in

REVIEW 10 cited by

Tina: Tiny Reasoning Models via LoRA

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2504.15777 v1 pith:RZV2D4YA submitted 2025-04-22 cs.CL cs.AIcs.LG

Shangshang Wang , Julian Asilis , Ömer Faruk Akgül , Enes Burak Bilgin , Ollie Liu , Willie Neiswanger This is my paper
classification cs.CLcs.AIcs.LG
keywords reasoningmodelmodelsloratinatinyachievedbase
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

How cost-effectively can strong reasoning abilities be achieved in language models? Driven by this fundamental question, we present Tina, a family of tiny reasoning models achieved with high cost-efficiency. Notably, Tina demonstrates that substantial reasoning performance can be developed using only minimal resources, by applying parameter-efficient updates during reinforcement learning (RL), using low-rank adaptation (LoRA), to an already tiny 1.5B parameter base model. This minimalist approach produces models that achieve reasoning performance which is competitive with, and sometimes surpasses, SOTA RL reasoning models built upon the same base model. Crucially, this is achieved at a tiny fraction of the computational post-training cost employed by existing SOTA models. In fact, the best Tina model achieves a >20\% reasoning performance increase and 43.33\% Pass@1 accuracy on AIME24, at only \$9 USD post-training and evaluation cost (i.e., an estimated 260x cost reduction). Our work reveals the surprising effectiveness of efficient RL reasoning via LoRA. We validate this across multiple open-source reasoning datasets and various ablation settings starting with a single, fixed set of hyperparameters. Furthermore, we hypothesize that this effectiveness and efficiency stem from LoRA rapidly adapting the model to the structural format of reasoning rewarded by RL, while largely preserving the base model's underlying knowledge. In service of accessibility and open research, we fully open-source all code, training logs, and model weights \& checkpoints.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning

    cs.CL 2026-05 unverdicted novelty 7.0 of 10

    RL improves LLM reasoning by sparse policy selection at high-entropy tokens rather than new capability learning, and a minimal RL-free method matches its gains at three orders of magnitude lower cost.

  2. Fine-Tuning Small Reasoning Models for Quantum Field Theory

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    Small 7B reasoning models were fine-tuned on synthetic and curated QFT problems using RL and SFT, yielding performance gains, error analysis, and public release of data and traces.

  3. ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    ALTO accelerates LoRA tuning up to 13.8x by monitoring loss trajectories for early stopping, using fused grouped GEMM with rank-local adapter parallelism, and combining intra- and inter-task scheduling for heterogeneo...

  4. LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A training method that recovers reinforcement-learning gradient on all-fail math prompts by fitting a temporary LoRA adapter, re-rolling, and splicing successful answers into the RL batch.

  5. Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    RL for LLM reasoning acts as sparse policy selection at high-entropy tokens already present in the base model, enabling ReasonMaxxer—an efficient contrastive method that recovers most RL gains at three orders of magni...

  6. Efficient Reasoning on the Edge

    cs.LG 2026-03 accept novelty 5.5 of 10

    LoRA adapters, budget-forced GRPO, dynamic switching, parallel verification and FPTQuant enable practical chain-of-thought reasoning on quantized Qwen2.5-7B for edge devices.

  7. The Hidden Power of Scaling Factor in LoRA Optimization

    cs.AI 2026-06 unverdicted novelty 5.0 of 10

    Alpha in LoRA outperforms learning-rate scaling, follows a square-root law with rank, and enables a minimalist LoRA-alpha method that improves performance across tasks.

  8. Learning from Less: Measuring the Effectiveness of RLVR in Low Data and Compute Regimes

    cs.AI 2026-04 unverdicted novelty 5.0 of 10

    Mixed-complexity procedural datasets provide up to 5x sample efficiency for RLVR on small models in low-data regimes, with low-to-high complexity generalization observed across counting, graph, and spatial tasks.

  9. PubSwap: Public-Data Off-Policy Coordination for Federated RLVR

    cs.LG 2026-04 unverdicted novelty 5.0 of 10

    PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.

  10. Low-Rank Adaptation Redux for Large Models

    cs.LG 2026-04 unverdicted novelty 3.0 of 10

    An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.

Pith tools