6arXiv cs.AI (Artificial Intelligence)·
MANTA: Framework for self-evolving multi-agent communication topology at inference time
MANTA is a new framework that allows multi-agent LLM systems to dynamically adapt their communication topology during inference rather than treating it as a fixed design choice. The system initializes a task-conditioned topology from prior structural experience, then monitors collaboration traces and applies bounded structural updates—modifying agent roles, communication links, execution order, and validation pathways—as needed. Evaluated across five benchmarks spanning information seeking, tool use, planning, workflow execution, and mathematical reasoning, MANTA achieves an average score of 74.0, outperforming the strongest baseline by 5.8 percentage points.
Related guides (2)
Related events (8)
MESA framework proactively ranks vulnerable communication channels in multi-agent systems
Researchers introduce MESA, a label-free framework for prioritizing security-critical communication edges in multi-agent systems (MAS) before attacks are observed. The framework combines six graph-theoretic metrics with two dynamic probes (ablation and masking) to rank edges by compromise risk, without requiring attack traces. Evaluated across three MAS scenarios, eight network topologies, and five open-source LLMs, MESA achieves mean Spearman ρ=+0.60 correlation with empirical per-edge attack success, and monitoring the top 10% of ranked edges intercepts roughly 3x more successful attacks than random allocation. The work highlights that attack impact in MAS is highly concentrated — a single compromised edge can account for up to 75% of total attack success.
LongMINT: Benchmark for Evaluating Memory Under Multi-Target Interference in Long-Horizon Agent Systems
LongMINT is a new benchmark designed to evaluate memory-augmented agents in realistic long-horizon settings where information is repeatedly updated and interferes across memories. It contains 15.6k QA pairs over contexts averaging 138.8k tokens (up to 1.8M tokens), spanning domains including state tracking, multi-turn dialogue, Wikipedia revisions, and GitHub commits. Evaluation of 7 representative systems—including vanilla long-context LLMs, RAG, and memory-augmented agent frameworks—reveals consistently low average accuracy of 27.9%, with performance particularly degraded on multi-target aggregation tasks and when earlier facts are revised by subsequent context. The analysis identifies retrieval and memory construction as the primary bottlenecks.
MLEvolve: Self-evolving multi-agent framework for automated ML algorithm discovery
MLEvolve is a new LLM-based multi-agent framework for end-to-end machine learning algorithm discovery, addressing limitations of existing MLE agents including information isolation and memoryless search. The system introduces Progressive MCGS (a graph-extended tree search), Retrospective Memory for experience accumulation, and decoupled strategic planning from code generation. Evaluated on MLE-Bench, it achieves state-of-the-art medal and valid submission rates within a 12-hour budget, and also outperforms AlphaEvolve on mathematical algorithm optimization tasks.
MA²P: A Meta-Cognitive Multi-Agent Framework for Complex Persuasion
The paper introduces MA²P, a multi-agent framework designed for complex persuasion tasks where the persuadee's internal states are latent. The system coordinates perception management, mental-state inference, strategy execution, memory, and evaluation modules, and adds a meta-cognitive configurator that selects domain-appropriate strategies from a structured knowledge base to reduce cross-domain performance variance. Experiments show higher persuasion success rates compared to baselines. The work addresses a known weakness of LLMs in producing generic or weakly grounded persuasive responses.
StreamMA: Streaming communication in multi-agent reasoning reduces latency and improves accuracy
Researchers introduce StreamMA, a multi-agent reasoning system that streams individual reasoning steps to downstream agents as they are generated, rather than waiting for a complete chain. This pipelining approach reduces end-to-end latency and also improves accuracy by shielding downstream agents from error-prone late reasoning steps. Evaluated across eight benchmarks, two frontier LLMs (Claude Opus 4.6 and GPT-5.4), and three topologies, StreamMA outperforms serial and single-agent baselines by an average of 7.3 percentage points. The paper also identifies a 'step-level scaling law' — a new scaling dimension orthogonal to agent-count scaling.
MyAG: Graph-based framework for composable LLM agent system design and analysis
Researchers introduce MyAG, an open-source framework that structures LLM agent systems using three graph abstractions: a component graph, a workflow graph, and a search graph for runtime execution. The separation enables flexible component reuse across different execution strategies, with support for hierarchical composition via recursive system nodes and built-in monitoring and visualization tools. Experiments on representative agent applications demonstrate performance-efficiency tradeoff analysis capabilities.
FluxMem: Connectivity-Evolving Memory Framework for LLM Agents
FluxMem proposes a heterogeneous graph-based memory framework for LLM agents that continuously evolves its topology through three stages: initial connection formation, feedback-driven refinement, and long-term consolidation. Unlike static memory repositories, FluxMem repairs missing links, prunes interference, aligns abstraction granularity, and distills successful trajectories into reusable procedural circuits. The system is guided by a single metric for memory generalizability and evolutionary maturity, achieving state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
Benchmark and study of LLM agents in deliberative multi-agent collaboration under partial observability
Researchers introduce a scalable benchmark for evaluating LLM agents on cooperative joint decision-making tasks where agents must exchange information under partial and asymmetric observations to reach a shared decision. A systematic evaluation of representative LLMs finds that state-of-the-art models still struggle with complex deliberative collaboration, failing in either information alignment or downstream reasoning even with external mathematical tools. Diagnostic analysis also reveals that deliberation can enable reflection and error correction, sometimes outperforming centralized baselines, offering a nuanced picture of multi-agent LLM capabilities.