Masaaki Nakatsu, Reno Wang · Oct 8, 2026 · Citations: 0
General
Multi-agent LLM systems negotiating with a stateful counterpart waste model calls in three ways: polite loops that never meet the counterpart's hidden acceptance condition, malformed outputs that trigger retries, and compliance deadlocks in…
In five runs per configuration (30 runs; Gemini 2.5 Pro agents, Claude Haiku 4.5 Gatekeeper) we find: (i) the constitution and Director make an acceptable framing possible but not reliable - 0/5 baseline unlocks versus 1/5 and 2/5 with the…
Adrián Zámečník, Matěj Kripner, Martin Koutecký, Martin Balko, Jan Grebík, Pavel Hubáček · Oct 7, 2026 · Citations: 0
Expert VerificationMath
We describe Bolzano, a multi-agent open-source system that uses parallel prover agents with a verifier agent and maintains a human-readable research state.
Motivated by these case studies, we ran Bolzano without problem-specific human guidance on about 3,800 open problems extracted from four sets of papers, solving about 200 open problems.
Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache memory binds.
We measure both on one three-tier agent architecture.
LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial content.
This study organizes defenses into five principles, implementing them as DEFER1 (DEterministic-First Enforcement with Residual judgment), which includes a cascade of 28 checks that blocks what it can and refers the rest to a panel of four…
Multi-agent simulations with large language models (LLMs) often operate networks of agents with a single base model.
To show this, we simulate a heterogeneous social network powered by several different base models and show that the amount of engagement an agent receives depends more on its base model than on its assigned persona.
In this paper, we propose MedPrune, an efficient medical multimodal multi-agent collaboration framework that dynamically prunes both nodes and edges from the communication topology to enhance reasoning ability and token efficiency.
Building on this graph, we introduce two sparsification mechanisms to enable adaptive collaborative evolution: (1) Heterogeneous Node Sparsification, which eliminates task-irrelevant specialist agents irrelevant to the current multimodal…
Stefan Bühler, David Exler, Markus Reischl, Mark Schutera · Oct 5, 2026 · Citations: 0
General
We contribute an open two-probe benchmark that can place any language model on this spectrum.
Applied to twelve language models, the benchmark shows that seven mostly follow the instruction in both probes and justify their action by pointing to the instruction.
Across Doc2Repo, NL2Repo, and CodeProjectEval, using closed- and open-source models including Opus-4.8 and DeepSeek-V4-Flash, AECP improves average test pass rate by 28.2% and reduces average wall time by 16.5% relative to an agent team…
Artifact-exclusive communication also blocks the relay of malicious instructions between agents, reducing how often they reach other agents from 95% to 0% and how often those agents act on them from 40% to 0%.
Frida Nøhr Laustsen, Marie Haahr Petersen, Victoria Popa, Ariel Flint, Romualdo Pastor-Satorras, Andrea Baronchelli · Oct 2, 2026 · Citations: 0
General
When two AI agents disagree, who persuades whom?
As multi-agent systems increasingly combine language models of different families and sizes, the answer can determine which judgments survive interaction.
Changxiu Ji, Amy Lu, Qizheng Zhang, Kunle Olukotun · Oct 2, 2026 · Citations: 0
General
LLM agents often fail mid-task due to invalid tool calls, repeated actions, or poorly grounded reasoning, and learning from these failures is a path to reliability.
We find that how failure knowledge reaches the agent matters as much as what it contains.
Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding agents that repeatedly reproduce code, logs, and earlier attempts.
We present AgSpec, a framework that supplies the corpus and draft-length policies that existing retrieval engines lack in coding-agent pipelines.
Chun-Wah Hsu, Kai Gong, Yu Wu, Xianhe Chen, Mengyang Liu, Jie Li · Sep 29, 2026 · Citations: 0
Coding
To this end, we introduce OpenCollab, a multi-agent coding framework that provides a unified infrastructure for programmable collaboration and controllable runtime.
Our experiments reveal that agents collaborate very differently across configurations: changing any single dimension shifts Adherence, from 47.2% to as high as 97.2%.
Complex tasks inherently couple workflow structure, agent responsibility, collaboration, and memory access: task regions delimit responsibility and tool scope, cross-region dependencies give rise to handoffs, and ownership boundaries…
We introduce TOCOMAS, a Topology-Coherent Multi-Agent System.
This allows the model to learn what is most important to maintain in context, and naturally extends to multi-agent systems where multiple agent contexts coexist as files.
Building CLMs zero-shot with existing models outperforms SOTA context management strategies across a variety of tasks: 11.4% higher accuracy with 21.5% fewer FLOPs on BrowseComp-Plus, 5% higher scores with 59% fewer FLOPs on 12-hour…
We propose LatCom, a cross-agent latent compression framework for efficient multi-agent latent collaboration.
Experiments on multiple benchmarks with Qwen3-4B show that LatCom achieves an average 2.46x inference speed-up over LatentMAS and reduces output token usage by 70.3% while maintaining comparable average accuracy.
Sen Zhao, Ruiqi Kong, Zuyu Zhang, Lifeng Shen, Xinyu He, Ding Zou · Sep 26, 2026 · Citations: 0
Automatic MetricsGeneral
Multi-agent workflows require task-relevant information to be shared across agents, while irrelevant, stale, unverified, or incompatible information must remain isolated.
We introduce CoMemBench, an execution-grounded benchmark for collaborative memory sharing and isolation across multi-agent workflow topologies.
