TRACER combines a controller-regret layer using regret matching for speak/skip decisions with a generation-credit layer using GSPO rewards to enable learned collaboration in multi-LLM reasoning.
and Zhang, Kaiqing and Kim, Joo-Kyung
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Mutual Reinforcement Learning allows heterogeneous LLMs to exchange experience through mechanisms like Peer Rollout Pooling, Cross-Policy GRPO Advantage Sharing, and Success-Gated Transfer, with outcome-level sharing identified as favorable on the stability-support trade-off.
Agentic AI systems with DAG topologies are claimed to deliver exponentially superior generalization and sample efficiency compared to monolithic scaling for achieving AGI.
citing papers explorer
-
TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning
TRACER combines a controller-regret layer using regret matching for speak/skip decisions with a generation-credit layer using GSPO rewards to enable learned collaboration in multi-LLM reasoning.
-
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
Mutual Reinforcement Learning allows heterogeneous LLMs to exchange experience through mechanisms like Peer Rollout Pooling, Cross-Policy GRPO Advantage Sharing, and Success-Gated Transfer, with outcome-level sharing identified as favorable on the stability-support trade-off.
-
Position: Agentic AI System Is a Foreseeable Pathway to AGI
Agentic AI systems with DAG topologies are claimed to deliver exponentially superior generalization and sample efficiency compared to monolithic scaling for achieving AGI.