REVIEW 22 cited by
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
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
read the original abstract
Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do these approaches efficiently utilize test-time compute? Would these approaches continue to scale as the budget improves? In this paper, we try to answer these questions. We formalize the problem of optimizing test-time compute as a meta-reinforcement learning (RL) problem, which provides a principled perspective on spending test-time compute. This perspective enables us to view the long output stream from the LLM as consisting of several episodes run at test time and leads us to use a notion of cumulative regret over output tokens as a way to measure the efficacy of test-time compute. Akin to how RL algorithms can best tradeoff exploration and exploitation over training, minimizing cumulative regret would also provide the best balance between exploration and exploitation in the token stream. While we show that state-of-the-art models do not minimize regret, one can do so by maximizing a dense reward bonus in conjunction with the outcome 0/1 reward RL. This bonus is the ''progress'' made by each subsequent block in the output stream, quantified by the change in the likelihood of eventual success. Using these insights, we develop Meta Reinforcement Fine-Tuning, or MRT, a new class of fine-tuning methods for optimizing test-time compute. MRT leads to a 2-3x relative gain in performance and roughly a 1.5x gain in token efficiency for math reasoning compared to outcome-reward RL.
Forward citations
Cited by 22 Pith papers
-
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
-
Addressing Over-Refusal in LLMs with Competing Rewards
SEAR trains one LLM via adversarial process rewards to explore harmful reasoning paths but flip to safe outputs, reducing over-refusal while preserving safety.
-
Learning Process Rewards via Success Visitation Matching for Efficient RL
Success Visitation Matching uses a discriminator to turn sparse outcome rewards into dense process rewards by matching visitations of successful episodes, provably preserving the optimal policy and speeding up robotic...
-
Understanding and Mitigating Premature Confidence for Better LLM Reasoning
Premature confidence in LLM chains of thought predicts flawed reasoning and is mitigated by progressive confidence shaping, a label-free RL objective that yields accuracy gains on arithmetic, math, and science tasks.
-
Hint Tuning: Less Data Makes Better Reasoners
Hint Tuning uses an instruct model as a difficulty probe to create 1K multi-level hint examples that train reasoning models to calibrate chain-of-thought length, cutting tokens by 31.5% on average across 4B-32B models...
-
Hint Tuning: Less Data Makes Better Reasoners
Hint Tuning reduces token usage 24-66% (31.5% avg) in reasoning models via 1K self-annotated samples aligned to an instruct model's capabilities while keeping benchmark accuracy.
-
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
CoRD uses collaborative multi-teacher step-wise decoding with perplexity-guided beam search to generate higher-quality Long-CoT data that lets smaller models reach near-teacher performance with less supervision.
-
GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
GRPO-VPS improves GRPO by using segment-wise conditional probabilities of the correct answer to supply process-level feedback, yielding up to 2.6-point accuracy gains and 13.7% shorter reasoning on math tasks.
-
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
-
ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning
ReRec uses reinforcement fine-tuning with dual-graph reward shaping, reasoning-aware advantage estimation, and online curriculum scheduling to improve LLM reasoning and performance in recommendation tasks.
-
Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
Group Causal Counterfactual Policy Optimization trains LLMs on generalizable reasoning by defining episodic rewards for counterfactual robustness and transferability then optimizing the policy with token-level advantages.
-
ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
ParaThinker trains LLMs for native parallel reasoning and reports 7 to 12 percent higher accuracy on math benchmarks over sequential thinking with modest latency overhead.
-
BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
A control-token insertion and two-stage training method that lets LLMs adhere to user-specified reasoning token budgets while preserving math accuracy.
-
Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning
A dual-penalty RL method that compresses chain-of-thought traces by separately penalizing internal semantic stagnation and external post-answer continuation reduces reasoning length by about 40% while preserving accur...
-
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
LRMs exhibit complete accuracy collapse beyond certain puzzle complexities, with reasoning effort rising then declining, outperforming standard LLMs only on medium-complexity tasks.
-
Structured Thoughts For Improved Reasoning And Context Pruning
Structured try/outcome SFT improves math reasoning by up to 8% over standard SFT and enables pruning ~85% of context with ~9% accuracy drop.
-
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
-
Placing Puzzle Pieces Where They Matter: A Question Augmentation Framework for Reinforcement Learning
PieceHint strategically scores and injects critical reasoning hints in RL training to let a 1.5B model match 32B baselines on math benchmarks while preserving pass@k diversity.
-
Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness
Thinking LLMs achieve ~10 percentage points higher accuracy than non-thinking ones on RewardBench with under 2x compute overhead, outperforming augmentation strategies that cost over 8x more while also showing better ...
-
ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
An open training recipe that teaches a 32B LLM to reason in three adjustable modes, cutting token use by half or three quarters with small accuracy losses.
-
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
-
Numerically Optimizing Shortcuts to Adiabaticity: A Hybrid Control Strategy
Combining analytical shortcuts to adiabaticity with numerical optimization yields up to 1000× better two-ion separation protocols without extra experimental cost.
Discussion (0). Sign in to comment.