GraphFlow uses a unified wGraph to dynamically instantiate workflows and manage KV caches for LLM agents, reporting 4.95 pp average gains and 4x memory reduction on five benchmarks.
hub Canonical reference
Tree of thoughts: Deliberate problem solving with large language models.Advances in neural information processing systems, 36:11809–11822, 2023a
Canonical reference. 100% of citing Pith papers cite this work as background.
15
Pith papers citing it
Background
100% of classified citations
abstract
Recent advances in LLM-based agent systems have shown promise on complex, long-horizon tasks, but existing agent protocols (e.g., A2A and MCP) do not adequately support lifecycle-aware coordination across agents, tools, and environments. To address this limitation, we introduce the \textbf{Tool-Environment-Agent} (TEA) protocol, a unified abstraction that models these components as first-class, versioned resources with explicit lifecycles. TEA supports end-to-end context and version management, improving traceability and reproducibility, while also enabling continual self-evolution of agent-associated components\footnote{Unless otherwise specified, \emph{agent-associated components} include prompts, memory/tool/agent/environment code, and agent outputs (solutions).}. Building on TEA, we present \projectname, a hierarchical multi-agent framework in which a central planner coordinates specialized sub-agents and dynamically extends capabilities during execution. Experiments on four challenging benchmarks, spanning expert-level agent tasks and scientific/mathematical reasoning, show that AgentOrchestra consistently outperforms strong baselines; in particular, it achieves 89.04\% on the GAIA Test set, placing it among the leading methods to the best of our knowledge. These results highlight the value of explicit protocol design and hierarchical orchestration for building more robust and adaptive multi-agent systems.
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
IdleSpec improves LLM agent accuracy by generating and aggregating speculative plans during idle time between tool calls and observations using complementary drafting strategies.
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
OMC framework turns multi-agent AI into self-organizing companies with Talents, Talent Market, and E²R search, achieving 84.67% success on PRDBench (15.48 points above prior art).
Discourse among AI agents on Moltbook is largely determined by architectural constraints like context windows and identity files, appearing as social learning but actually short-horizon contextual conditioning.
AURA improves implicit-need coverage by 0.07 over ReAct baselines on a 100-query benchmark by inserting an intent inference step controlled by a gap score, while cutting probes 82% on factual tasks.
A manager-driven DAG decomposition with parallel subagents improves computer use agent success rates by 3.4-25.5% and reduces wall-clock time on long-horizon benchmarks.
Complete cyclic subtask graphs offer a lens to measure when multi-agent revisitation aids recovery and exploration versus when it increases costs or is dominated by other bottlenecks in LLM agent workflows.
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
CONCAT introduces a consensus- and confidence-driven ad hoc teaming method that reduces communication overhead in LLM-based multi-agent systems by up to 50% latency while improving efficiency ratio without any training.
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
A multi-agent SDD framework with phase-level context-grounding hooks improves LLM-judged quality by 0.15 points and SWE-bench Lite Pass@1 by 1.7 percent while preserving near-perfect test compatibility.
Structured query and evidence tools added to an AI research agent improve benchmark accuracy by 0.6 to 3.8 percentage points.
Qualixar OS provides a runtime for multi-agent AI systems with support for 12 topologies, LLM-driven team design, dynamic routing, consensus judging, content attribution, and protocol bridging, achieving 100% accuracy on a custom 20-task suite at $0.000039 mean cost per task.
ActionNex is an agentic system for cloud outage management that compresses multimodal signals into critical events, uses hierarchical memory for reasoning, and recommends actions with 71.4% precision on real Azure outages.
citing papers explorer
-
GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving
GraphFlow uses a unified wGraph to dynamically instantiate workflows and manage KV caches for LLM agents, reporting 4.95 pp average gains and 4x memory reduction on five benchmarks.
-
IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents
IdleSpec improves LLM agent accuracy by generating and aggregating speculative plans during idle time between tool calls and observations using complementary drafting strategies.
-
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
-
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
OMC framework turns multi-agent AI into self-organizing companies with Talents, Talent Market, and E²R search, achieving 84.67% success on PRDBench (15.48 points above prior art).
-
What Do AI Agents Talk About? Discourse and Architectural Constraints in the First AI-Only Social Network
Discourse among AI agents on Moltbook is largely determined by architectural constraints like context windows and identity files, appearing as social learning but actually short-horizon contextual conditioning.
-
AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents
AURA improves implicit-need coverage by 0.07 over ReAct baselines on a 100-query benchmark by inserting an intent inference step controlled by a gap score, while cutting probes 82% on factual tasks.
-
Multi-Agent Computer Use
A manager-driven DAG decomposition with parallel subagents improves computer use agent success rates by 3.4-25.5% and reduces wall-clock time on long-horizon benchmarks.
-
Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows
Complete cyclic subtask graphs offer a lens to measure when multi-agent revisitation aids recovery and exploration versus when it increases costs or is dominated by other bottlenecks in LLM agent workflows.
-
CONCAT: Consensus- and Confidence-Driven Ad Hoc Teaming for Efficient LLM-Based Multi-Agent Systems
CONCAT introduces a consensus- and confidence-driven ad hoc teaming method that reduces communication overhead in LLM-based multi-agent systems by up to 50% latency while improving efficiency ratio without any training.
-
Heterogeneous Scientific Foundation Model Collaboration
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
-
Spec Kit Agents: Context-Grounded Agentic Workflows
A multi-agent SDD framework with phase-level context-grounding hooks improves LLM-judged quality by 0.15 points and SWE-bench Lite Pass@1 by 1.7 percent while preserving near-perfect test compatibility.
-
EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
Structured query and evidence tools added to an AI research agent improve benchmark accuracy by 0.6 to 3.8 percentage points.
-
Qualixar OS: A Universal Operating System for AI Agent Orchestration
Qualixar OS provides a runtime for multi-agent AI systems with support for 12 topologies, LLM-driven team design, dynamic routing, consensus judging, content attribution, and protocol bridging, achieving 100% accuracy on a custom 20-task suite at $0.000039 mean cost per task.
-
ActionNex: A Virtual Outage Manager for Cloud Computing
ActionNex is an agentic system for cloud outage management that compresses multimodal signals into critical events, uses hierarchical memory for reasoning, and recommends actions with 71.4% precision on real Azure outages.