REVIEW 18 cited by
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
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
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
read the original abstract
Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains challenging, as existing methods predominantly rely on supervised fine-tuning (SFT) over synthetic data, which encourages teacher-forced imitation rather than exploration and generalization. Different from them, we propose \textbf{Parallel-R1}, the first reinforcement learning (RL) framework that enables parallel thinking behaviors for complex real-world reasoning tasks. Our framework employs a progressive curriculum that explicitly addresses the cold-start problem in training parallel thinking with RL. We first use SFT on prompt-generated trajectories from easier tasks to instill the parallel thinking ability, then transition to RL to explore and generalize this skill on harder problems. Experiments on various math benchmarks, including MATH, AMC23, and AIME, show that Parallel-R1 successfully instills parallel thinking, leading to 8.4% accuracy improvements over the sequential thinking model trained directly on challenging tasks with RL. Further analysis reveals a clear shift in the model's thinking behavior: at an early stage, it uses parallel thinking as an exploration strategy, while in a later stage, it uses the same capability for multi-perspective verification. Most significantly, we validate parallel thinking as a \textbf{mid-training exploration scaffold}, where this temporary exploratory phase unlocks a higher performance ceiling after RL, yielding a 42.9% improvement over the baseline on AIME25. Our model, data, and code will be open-source at https://github.com/zhengkid/Parallel-R1.
Forward citations
Cited by 18 Pith papers
-
Regulating Branch Parallelism in LLM Serving
TAPER regulates LLM branch parallelism by admitting extra branches opportunistically when predicted externality fits slack, delivering 1.48-1.77x higher goodput than eager or fixed-cap baselines on Qwen3-32B while kee...
-
On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency
Parallel thinking in LLMs suffers from overscaling where fixed global budgets waste samples; LanBo predicts per-sample budgets from latent states to raise utilization without hurting accuracy.
-
LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents
LangDriveCTRL decomposes driving videos into 3D scene graphs and uses an agentic pipeline with specialized multi-modal agents to perform language-controlled object and behavior edits, achieving nearly 2x higher instru...
-
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
Scaling zero-RL training to a 1T-parameter model yields competitive math performance and spontaneous cognitive behaviors such as self-verification and structured formatting.
-
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
A trillion-parameter model trained purely on reward feedback reaches competitive math scores and produces structured, self-verifying reasoning traces, but the claim that these behaviors emerge without hand-crafted rul...
-
Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling
RL-trained lightweight controller using answer statistics improves trade-offs among correctness, latency, and total samples in adaptive sampling for LLM test-time scaling.
-
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
DeltaRubric decomposes multimodal preference evaluation into self-generated planning and verification steps within a single model, producing large accuracy improvements on VL-RewardBench via multi-role reinforcement learning.
-
Reinforcing Multimodal Reasoning Against Visual Degradation
ROMA improves MLLM robustness to seen and unseen visual corruptions by +2.3-2.4% over GRPO on seven reasoning benchmarks while matching clean accuracy.
-
The Scaling Properties of Implicit Deductive Reasoning in Transformers
With shortcut-decorrelated training, bidirectional masking, and a corrective objective, depth scaling makes direct transformer reasoning over Horn clauses match CoT accuracy within the training horizon, but not beyond it.
-
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
A parameter-free sampling strategy called CUTS combined with Mixed-CUTS training prevents mode collapse in RL for saturated LLM reasoning tasks and raises AIME25 Pass@1 accuracy by up to 15.1% over standard GRPO.
-
LACE: Lattice Attention for Cross-thread Exploration
LACE enables parallel reasoning paths in LLMs to communicate via lattice attention and error-correct using synthetic training data, improving accuracy by over 7 points over standard parallel search.
-
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
NPR trains LLMs to reason in parallel via self-distilled RL, delivering up to 24.5% performance gains and 4.6x speedups with 100% genuine parallel execution on reasoning benchmarks.
-
StatEval: A Comprehensive Benchmark for Large Language Models in Statistics
StatEval is a new 16,000-question statistics benchmark showing that even strong LLMs score below 60% on research-level statistical proof tasks.
-
Efficient Reasoning on the Edge
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.
-
The Scaling Properties of Implicit Deductive Reasoning in Transformers
In deep Transformers using bidirectional prefix masks, implicit reasoning on Horn clauses matches explicit CoT performance across topologies and widths, but CoT is still required for depth extrapolation.
-
LACE: Lattice Attention for Cross-thread Exploration
LACE enables concurrent reasoning paths in LLMs to interact via lattice attention and a synthetic training pipeline, raising accuracy more than 7 points over independent parallel search.
-
LACE: Lattice Attention for Cross-thread Exploration
LACE adds lattice attention to let parallel LLM reasoning threads interact and correct errors, raising accuracy over 7 points versus standard independent sampling.
-
Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models
Lack of exploration from conditioning on prior answers is the primary reason parallel sampling outperforms sequential sampling in large reasoning models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.