Pith. sign in

REVIEW 7 cited by

Tina: Tiny Reasoning Models via LoRA

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

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). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. 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.

  2. Resa: Transparent Reasoning Models via SAEs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    SAE-Tuning, a sparse-autoencoder-guided SFT procedure, elicits RL-comparable reasoning in 1.5B models from CoT-free QA data at about $1 and 20 minutes of training.

  3. RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion

    cs.LG 2025-05 conditional novelty 6.0 of 10

    RECIPE-TKG combines rule-based multi-hop history sampling, contrastive LoRA fine-tuning, and test-time semantic filtering to improve LLM temporal knowledge graph completion, with Hits@10 gains up to 30.6% over prior L...

  4. The Hallucination Tax of Reinforcement Finetuning

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Standard RFT sharply reduces LLM refusal on unanswerable questions, and adding 10% synthetic unanswerable math during RFT restores refusal with small accuracy losses.

  5. 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.

  6. Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters

    stat.ML 2025-06 reject novelty 5.0 of 10

    The paper proves an upper bound of about sqrt(r/N) on the LoRA generalization gap and claims a matching lower bound, but both proofs contain structural gaps.

  7. Get Experience from Practice: LLM Agents with Record & Replay

    cs.LG 2025-05 reject novelty 4.0 of 10

    AgentRR is a proposed paradigm that records agent traces, generalizes them into multi-level experiences, and replays them under safety checks to make LLM agents cheaper, faster, and more reliable.

Pith tools