TacoMAS performs test-time co-evolution of agent capabilities and communication topology in LLM multi-agent systems via fast capability updates and slow meta-LLM topology edits, delivering 13.3% average gains over strong baselines on four benchmarks.
hub
arXiv preprint arXiv:2410.06153 , year=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
AgentCo-op retrieves and assembles existing agents and tools into interoperable workflows for open-world scientific tasks, showing effectiveness in genomics case studies and competitive benchmark results with lower costs.
Partial harnesses for LLM agents, specifying only initial execution steps, achieve higher pass rates than fully decomposed workflows, as analyzed through trajectory alignment and validated in synthetic and terminal benchmarks.
LLM agents trained with a task-success reward on self-generated knowledge can spontaneously explore and adapt to new environments without any rewards or instructions at inference, yielding 20% gains on web tasks and allowing a 14B model to beat Gemini-2.5-Flash.
AgentGA optimizes agent seeds with genetic algorithms and parent-archive inheritance to improve autonomous code generation, beating a baseline on 15 of 16 Kaggle competitions.
A eight-agent system automatically reproduces and improves SOTA models from top AI papers, reporting 105 surpassing variants on a curated 125-paper set.
MobiBench reaches near-human offline evaluation fidelity for mobile GUI agents by accepting any valid action at each step, and enables modular attribution of performance to agent components.
GTD generates task-adaptive, sparse communication topologies for multi-LLM agents via guided iterative graph diffusion steered by a proxy model predicting accuracy, utility, and cost.
SkillDisCo distills reusable PFSM subgraphs from successful agent traces and compiles them into callable procedural skills, improving success rates and reducing turns on ALFWorld and WebArena.
The paper surveys reinforced reasoning techniques for LLMs, covering automated data construction, learning-to-reason methods, and test-time scaling as steps toward Large Reasoning Models.
citing papers explorer
-
TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems
TacoMAS performs test-time co-evolution of agent capabilities and communication topology in LLM multi-agent systems via fast capability updates and slow meta-LLM topology edits, delivering 13.3% average gains over strong baselines on four benchmarks.
-
AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows
AgentCo-op retrieves and assembles existing agents and tools into interoperable workflows for open-world scientific tasks, showing effectiveness in genomics case studies and competitive benchmark results with lower costs.
-
Harnesses for Inference-Time Alignment over Execution Trajectories
Partial harnesses for LLM agents, specifying only initial execution steps, achieve higher pass rates than fully decomposed workflows, as analyzed through trajectory alignment and validated in synthetic and terminal benchmarks.
-
Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
LLM agents trained with a task-success reward on self-generated knowledge can spontaneously explore and adapt to new environments without any rewards or instructions at inference, yielding 20% gains on web tasks and allowing a 14B model to beat Gemini-2.5-Flash.
-
AgentGA: Evolving Code Solutions in Agent-Seed Space
AgentGA optimizes agent seeds with genetic algorithms and parent-archive inheritance to improve autonomous code generation, beating a baseline on 15 of 16 Kaggle competitions.
-
AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery
A eight-agent system automatically reproduces and improves SOTA models from top AI papers, reporting 105 surpassing variants on a curated 125-paper set.
-
MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents
MobiBench reaches near-human offline evaluation fidelity for mobile GUI agents by accepting any valid action at each step, and enables modular attribution of performance to agent components.
-
Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models
GTD generates task-adaptive, sparse communication topologies for multi-LLM agents via guided iterative graph diffusion steered by a proxy model predicting accuracy, utility, and cost.
-
SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
SkillDisCo distills reusable PFSM subgraphs from successful agent traces and compiles them into callable procedural skills, improving success rates and reducing turns on ALFWorld and WebArena.
-
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
The paper surveys reinforced reasoning techniques for LLMs, covering automated data construction, learning-to-reason methods, and test-time scaling as steps toward Large Reasoning Models.
- Tools as Continuous Flow for Evolving Agentic Reasoning