pith. sign in

A gent D ropout: Dynamic agent elimination for token-efficient and high-performance LLM -based multi-agent collaboration

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.CL 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Learning to Interrupt in Language-based Multi-agent Communication

cs.CL · 2026-04-07 · unverdicted · novelty 7.0

HANDRAISER learns optimal interruption points in multi-agent LLM communication using estimated future reward and cost, achieving 32.2% lower communication cost with comparable or better task results across games, scheduling, and debate.

citing papers explorer

Showing 2 of 2 citing papers.

  • Learning to Interrupt in Language-based Multi-agent Communication cs.CL · 2026-04-07 · unverdicted · none · ref 38

    HANDRAISER learns optimal interruption points in multi-agent LLM communication using estimated future reward and cost, achieving 32.2% lower communication cost with comparable or better task results across games, scheduling, and debate.

  • MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems cs.AI · 2026-05-07 · unverdicted · none · ref 11

    MASPO jointly optimizes prompts in multi-agent LLM systems via downstream-success evaluation and evolutionary beam search, delivering 2.9 average accuracy gains over prior methods across six tasks.