REVIEW 7 cited by
Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative 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
read the original abstract
Multi-agent systems (MAS) built on large language models (LLMs) offer a promising path toward solving complex, real-world tasks that single-agent systems often struggle to manage. While recent advancements in test-time scaling (TTS) have significantly improved single-agent performance on challenging reasoning tasks, how to effectively scale collaboration and reasoning in MAS remains an open question. In this work, we introduce an adaptive multi-agent framework designed to enhance collaborative reasoning through both model-level training and system-level coordination. We construct M500, a high-quality dataset containing 500 multi-agent collaborative reasoning traces, and fine-tune Qwen2.5-32B-Instruct on this dataset to produce M1-32B, a model optimized for multi-agent collaboration. To further enable adaptive reasoning, we propose a novel CEO agent that dynamically manages the discussion process, guiding agent collaboration and adjusting reasoning depth for more effective problem-solving. Evaluated in an open-source MAS across a range of tasks-including general understanding, mathematical reasoning, and coding-our system significantly outperforms strong baselines. For instance, M1-32B achieves 12% improvement on GPQA-Diamond, 41% on AIME2024, and 10% on MBPP-Sanitized, matching the performance of state-of-the-art models like DeepSeek-R1 on some tasks. These results highlight the importance of both learned collaboration and adaptive coordination in scaling multi-agent reasoning. Code is available at https://github.com/jincan333/MAS-TTS
Forward citations
Cited by 7 Pith papers
-
A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search
A skill-graph random-walk model gives closed-form accuracy-versus-compute formulas for four reasoning strategies and connects them to training scaling.
-
EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models
EMO-R3, which combines a three-step emotional reasoning prompt with a reward for the model agreeing with its own image–emotion judgments, raises visual emotion-recognition accuracy by about one point over plain GRPO.
-
How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs
A leader LLM trained with a GRPO variant that conditions on frozen agent responses improves both collaborative and zero-shot accuracy on BBH, MATH, and MMLU.
-
Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning
ADAPT, a diversity-aware prefix fine-tuning method, improves best-of-N sampling efficiency for a 1.5B reasoning model, reaching 80% accuracy at N=32 versus N=256 for the baseline.
-
CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
CoNav lets a frozen 3D-text model pass spatial text hints to a lightly fine-tuned image-text navigation agent, improving path efficiency on several VLN benchmarks, though not all claimed state-of-the-art results hold.
-
DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning
Multi-agent reasoning gains can be written as coverage × selection accuracy, which is a conditioning identity rather than a new decomposition; the PRISM system still shows moderate benchmark gains.
-
Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
A probabilistic saturation model for test-time scaling is proposed and fitted to reasoning benchmarks, but the plateau 'prediction' is computed from the same per-problem data used to measure it.
Discussion (0). Sign in to comment.