arXiv AI
SRPO: Setwise Relative Policy Optimization for Multi-Agent Systems
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 10
SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs
arXiv:2609.08452v1 Announce Type: new Abstract: Multi-agent large language models solve complex tasks by coordinating several policies in a shared environment. However, existing reinforcement learnin...
arXiv AI
Aug 13
Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning
arXiv:2608. 11658v1 Announce Type: cross Abstract: Many reinforcement learning systems, from fleet management to traffic signal control, must serve an objective that changes dynamically after deployment, and retraining a policy for each new objective is prohibitively expensive.
arXiv AI
Jul 23
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
arXiv:2510. 05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios.
arXiv AI
Jul 9
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
arXiv:2607. 07178v1 Announce Type: cross Abstract: Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks.
arXiv Machine Learning
Sep 1
Constrained Group Relative Policy Optimization
arXiv:2602.05863v3 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) remains the dominant critic-free approach for fine-tuning LLMs and VLMs, but its compatibility with const...
arXiv AI
Sep 15
HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning
arXiv:2609.13739v1 Announce Type: cross Abstract: Language-model agents are increasingly deployed through diverse harnesses that differ in system prompts, tool schemas, control loops, and trajectory...