REVIEW 15 cited by
SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
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
SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
abstract
Recent advances in inference-time compute have significantly improved performance on complex tasks by generating long chains of thought (CoTs) using Large Reasoning Models (LRMs). However, this improved accuracy comes at the cost of high inference latency due to the length of generated reasoning sequences and the autoregressive nature of decoding. Our key insight in tackling these overheads is that LRM inference, and the reasoning that it embeds, is highly tolerant of approximations: complex tasks are typically broken down into simpler steps, each of which brings utility based on the semantic insight it provides for downstream steps rather than the exact tokens it generates. Accordingly, we introduce SpecReason, a system that automatically accelerates LRM inference by using a lightweight model to (speculatively) carry out simpler intermediate reasoning steps and reserving the costly base model only to assess (and potentially correct) the speculated outputs. Importantly, SpecReason's focus on exploiting the semantic flexibility of thinking tokens in preserving final-answer accuracy is complementary to prior speculation techniques, most notably speculative decoding, which demands token-level equivalence at each step. Across a variety of reasoning benchmarks, SpecReason achieves $1.4-3.0\times$ speedup over vanilla LRM inference while improving accuracy by $0.4-9.0\%$. Compared to speculative decoding without SpecReason, their combination yields an additional $8.8-58.0\%$ latency reduction. We open-source SpecReason at https://github.com/ruipeterpan/specreason.
Forward citations
Cited by 15 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.
-
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
SpecGuard adds step-level verification to speculative decoding via attention grounding and log-probability scores, yielding 3.6% higher accuracy and 11% lower latency on reasoning benchmarks.
-
TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models
TrigReason matches large reasoning model accuracy on math and science benchmarks by delegating most steps to small models and intervening selectively on three triggers, cutting latency by 43.9% and cost by 73.3%.
-
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
A small tool-free MLLM plus answer-separability gating bypasses agentic tool loops for many queries, yielding 1.1–3.35× speedup with preserved or higher accuracy.
-
SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling
SafeSpec integrates a latent safety head into speculative LLM decoding with rollback and reflective multi-sampling, cutting attack success rates 15% on Qwen3-32B while retaining 2.06x speedup on normal workloads.
-
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
SPEX accelerates Tree-of-Thought LLM reasoning 1.2-3x via speculative path selection, dynamic budget allocation across queries, and adaptive early termination, with up to 4.1x when combined with token speculative decoding.
-
Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration
SPEX delivers 1.2-3x speedup on ToT algorithms via speculative path selection, dynamic budget allocation, and adaptive early termination, reaching up to 4.1x when combined with token-level speculative decoding.
-
Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents
Slipstream uses asynchronous compaction with trajectory-grounded judge validation to improve long-horizon agent accuracy by up to 8.8 percentage points and reduce latency by up to 39.7%.
-
Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
A small RL-trained policy for stepwise model routing between LLM sizes improves the accuracy-cost tradeoff on math benchmarks over handcrafted strategies and matches large process reward model methods.
-
Select to Think: Unlocking SLM Potential with Local Sufficiency
Small language models can achieve near large-model reasoning performance by learning to re-rank their own top-K token predictions after distilling selection from the large model.
-
GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts
GlimpRouter uses the entropy of the first token in each reasoning step to decide whether to invoke a large model, yielding 10.7% higher accuracy and 25.9% lower latency than a standalone large model on AIME25.
-
Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
N-gram based speculative decoding methods, especially SAM and hybrid SAM[EAGLE-3], achieve strong speedups in LLM test-time scaling by exploiting repetitive reasoning patterns.
-
Select to Think: Unlocking SLM Potential with Local Sufficiency
Select to Think reframes LLM help as ranking among SLM top-K candidates and distills the ranking ability back into the SLM for improved single-pass reasoning.
-
MixReasoning: Switching Modes to Think
A reasoning model can cut token usage by roughly a third to a half without losing accuracy if it switches to brief output on low-uncertainty steps and expands only at high-uncertainty forks.
-
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.