arXane › Computer Science › Computer Science
Wednesday, 4 November 2026: 7 new papers, 12 cross-lists and 9 replacements in Multiagent Systems (cs.MA), in arXiv's order, with full abstracts. The same papers as arXiv's own listing, set as a newspaper; every title links to arXiv.
Roles in multi-agent large language model (LLM) systems allocate decisions as well as work. In a Planner--Executor--Reviewer team, the Reviewer's approval can determine when the team submits an answer and receives corrective feedback. We study both functions by varying role instructions while holding agents, topology, call budget, and ground-truth evaluator constant, using three open-weight models on Omni-MATH and two on SciBench. Removing roles largely eliminates functional specialization without lowering first-pass accuracy. After a failed first answer, however, submission decisions matter: a role-structured Reviewer often withholds approval, so its team submits less often and receives fewer evaluator verdicts. In an exploratory comparison with feedback available to both teams, the role-free team recovers more often across all five model--benchmark settings. Two further analyses support the importance of feedback opportunities. In a post hoc comparison at equal numbers of verdicts, the pooled recovery difference is small (role-structured minus role-free: $+0.009$, 95% interval $[-0.014,+0.033]$). In an exploratory intervention on $400$ Omni-MATH problems with gemma-4, keeping the role prompts but forcing submission in every cycle raises recovery from $0.198$ to $0.613$; the paired comparison detects no difference from the role-free team. The takeaway is to evaluate roles through recovery after failure as well as specialization. For systems with reliable external feedback, this requires measuring who may submit, how often the team receives feedback, and which agents can act on it.
Must long-horizon AI investment research be rewritten every time stock prices move? Using 8,120 production reports on the same 203 stocks across four iPulse AI batches, we compare repricing existing targets, guarding them against price shocks, mechanically resetting old forecast growth, and generating fresh multi-agent reports. Ten matched configurations represent seven investment frameworks. Our primary economic evaluation selects Top 10 USD portfolios using one-year forecasts. Across two unchanged-model windows, guarded reuse averages 2.25%, versus 1.66% for SPY and 4.77% for fresh reports, after modeled trading costs and reference compute charges on a USD 100,000 account. Guarded reuse beats SPY in all three short windows, including the model-change transition. Extending the first holding window to nearly six months reverses the result: guarded reuse returns -11.26%, fresh reports +9.12%, and SPY +3.46%, motivating the thesis half-life question. Supporting quarter-forecast diagnostics show that mechanically re-anchoring old growth paths closes 98% of the MAE improvement over fixed targets, yet Fresh and Reset share only 1-4 of their Top 10 stocks. At Top 30, the unchanged-model portfolio comparison instead favors guarded reuse (4.17% versus 1.88%). Endpoint and concentration tests reveal the influence of horizon choices and exceptional winners. Nine production editions show substantial between-edition turnover, while every final editorial screen retains its own incoming list. Measured token workloads connect refresh costs to shared capital and realized break-even budgets. The resulting architecture separates continuous price monitoring from episodic thesis rebuilding and targeted editorial evidence checks.
The Weapon-Target Assignment (WTA) problem in distributed multi-agent systems is challenged by limited situational awareness and communication constraints. Existing distributed methods, such as auction-consensus algorithms, typically assume task-value independence, a simplification that fails to capture the coupled effects of multi-weapon assignments. This paper introduces the Distributed Marginal Return (DMR) algorithm, a novel decentralized approach that generalizes auction-consensus frameworks. DMR enables agents to compute bids based on marginal return and uses a consensus protocol to resolve conflicts, allowing multiple non-conflicting proposals to be accepted in parallel for cooperative optimization with minimal communication. A key theoretical contribution is our proof that the marginal returns of non-conflicting bids are additive, a property that ensures global consistency and validates our parallel acceptance mechanism. Extensive simulations demonstrate that DMR significantly outperforms baseline algorithms in both solution quality and communication efficiency, offering a scalable and robust solution for real-world distributed command and control applications.
Multimodal large language models (MLLMs) increasingly address knowledge-intensive tasks by integrating evidence scattered across multiple document pages into a final answer. Because such answers are synthesized from many pages, the link between the answer and its supporting visual evidence can become obscured, hindering verification and trust. Cross-page visual attribution is therefore essential: it requires identifying the supporting pages and localizing fine-grained evidence regions within them, thereby making multi-page reasoning transparent and auditable. Existing approaches either process multiple pages jointly or iteratively refine evidence within a single trajectory, risking cross-page context pollution and, for interactive methods, substantial sequential overhead. We introduce \textbf{AttriSwarm}, an agent-swarm framework that assigns these concerns to separate roles: a leader handles global cross-page reasoning, while subagents perform page-wise attribution in isolation and in parallel. To support training and evaluation, we construct \textbf{AttriDoc}, a cross-page QA dataset linking supporting pages to their annotated evidence regions, and use it for role-specific training of AttriSwarm, improving answer accuracy, page-level $F_1$, and region-level IoU over its training-free counterpart by an average of 18.94, 29.34, and 23.04 percentage points, respectively, across three open-source backbones and three datasets.
Science is a process of useful models being proven wrong time and again, but despite its many flaws, it somehow works. Why is this? Paul Feyerabend argued that it works because people dare to hold and defend incompatible rival theories against the accepted one, since a theory's failures often lead to its abandonment in the presence of a more accurate or simpler alternative. He called this view theoretical pluralism. We introduce a theoretical and experimental model in which this can be examined. It compares communities of pluralist agents, which can hold rival theories side by side and maintain beliefs within and between those theories, with communities of monist agents, which can only incorporate what they hear or observe into a single model of their own. In a multi-agent variational inference setting, our experimental demonstrations illustrate how communities with rival theories can go through periods of uncertainty followed by a shift in the theories they hold true, how the information that is communicated between communities affects beliefs when those communities make different observations about the world, and how sharing support for theories and sharing beliefs within them contribute differently to collective belief dynamics.
We address the problem of smooth continuous multi-agent path finding (SC-MAPF), where agents move in a continuous environment along smooth curves in continuous time. The paths for individual agents are searched in local visibility roadmaps that consider obstacles and other agents. A new algorithm is proposed in this work, which combines the previous algorithm CE-CBS for high-level search with any-angle path finding for local single-agent planning, where agents are to avoid obstacles, both static and other agents. The new algorithm is tested and compared to CE-CBS, the algorithm building individual paths using RRT$^*$, and SMT-CCBS algorithm, an algorithm for MAPF$_R$. Experimental results show various advantages of the new algorithm over CE-CBS and SMT-CCBS in comparable settings.
Real-world geospatial decision support requires more than single-step retrieval or code generation. Disaster-response questions often involve multi-source workflows that combine spatial databases, map-derived features, satellite imagery, raster products, and reusable geospatial artifacts, where correctness depends on preserving spatial scope, temporal context, and intermediate execution state. While large language models and coding agents offer a promising interface for such workflows, they struggle with geospatial-specific failure modes, including handling large artifacts, selecting the wrong evidence source, losing spatial or temporal metadata, and applying invalid geometric operations. We introduce GeoFaham, a domain-specialized multi-agent system for geospatial disaster analytics. GeoFaham decomposes workflows into specialist agents for vector operations, map feature retrieval, imagery discovery, and raster analysis, coordinated by an Orchestrator with a dual-ledger control loop for dependency-aware planning, progress tracking, validation, and replanning. To support artifact-centric collaboration, GeoFaham uses a Response Store that persists full geospatial outputs and typed metadata outside the LLM context window while agents exchange compact identifiers and summaries. We also introduce GeoFaham-Bench, a 40-task benchmark grounded in 17 real-world disaster records, designed to evaluate multi-step geospatial reasoning, cross-source integration, raster-vector computation, artifact generation, and recovery under non-rigid ground truth. We evaluate GeoFaham on GeoFaham-Bench against strong general-purpose coding-agent baselines, including Codex, Claude Code, and OpenCode. GeoFaham achieves the best overall performance, scoring 0.940 versus the next-best 0.879, while using 7.5 times fewer tokens. Our code and benchmark are publicly available at https://github.com/microsoft/GeoFaham.
Computational drug discovery offers a growing range of tools for proposing and evaluating molecules, but combining them and deciding what to do next still requires substantial expert effort. Here, we introduce El Agente F\'armaco, an AI scientist that uses modern large language model (LLM) technology to turn discovery goals expressed in everyday language into complex, scalable computational screening workflows. The agentic harness selects scientific tools, reviews their results, and adjusts subsequent steps to the target and the user's objectives. Our approach centers on a shared scientific memory: F\'armaco Atlas, which stores molecules, structures, and results together with their provenance -- a record of how they were obtained. The agent uses targeted database queries to retrieve the evidence needed for each decision. A single request can launch calculations for an entire collection of molecules, without requiring a separate LLM decision for every compound. This design limits the information the model must process as screening collections grow, while keeping the underlying results available for inspection and further analysis. The integrated tools support molecule generation, prediction of binding and molecular properties, and searches for compounds available for purchase. In a retrospective comparison with an expert-led campaign, the agent proposed chemically distinct candidates with competitive docking scores and higher calculated drug-likeness under explicitly imposed selection criteria. In a 22-task benchmark against plain tool calls and Codex, the agent achieved the highest observed mean model-judged score, with lower median cumulative token use and peak context. F\'armaco provides a foundation for flexible, scalable drug discovery workflows that connect scientific reasoning with an enduring, traceable record of computational work.
De-siloing can create groupthink; silos can prevent knowledge sharing and reduce research efficiency. The same tension appears in research systems built with large language model (LLM) agents, yet their organization is usually fixed by design. I propose treating laboratory structure and information sharing as experimental variables. I introduce Labtune, an open framework for bounded research workflows with user-selected laboratory organization, communication policy, model configuration and budget. Users can choose among six editable designs, from multidisciplinary silos and transdisciplinary teams to co-leaders, hub-and-spoke structures, flat co-labs and a single scientist. Information sharing can independently vary from none to high detail, with an optional channel for conditional abstractions called wisdom. Sharing is enforced by the controller at phase barriers rather than through unrestricted agent chat, while delegation does not create additional budget or permissions. Development evidence is separated from protected confirmation, and an optional multi-lab layer allows laboratories with different structures to exchange filtered information. Labtune is an idea and system-description paper, not a benchmark result. Its contribution is to make laboratory organization and information sharing configurable and measurable under matched budgets. I do not claim that one design or level of sharing is best; the aim is to create a concrete experimental space in which those differences can be tested.
Translating population-level exercise guidance into individualized prescriptions requires integrating clinical and wearable data, including diagnoses, medications, functional limitations, and baseline activity, with condition-specific recommendations, a process difficult to scale beyond specialist rehabilitation settings. We developed FITTER, a multi-agent framework that integrates these data with condition-specific guidance to generate personalized FITT-VP prescriptions and applies deterministic safety audit and repair to correct rule-checkable violations. We evaluated FITTER using data from 400 All of Us participants (300 cancer, 100 stroke) against five LLM comparators through computational evaluation, ablation, and structured clinician review. FITTER achieved 98.5% safety-constraint compliance versus 75.8-85.8% for comparators and showed greater quantitative dosing precision and guideline alignment. Cancer-cohort ablation identified safety audit and repair as the largest contributor to safety-constraint compliance. Clinicians reviewed 80 prescriptions across safety, personalization, instruction concreteness, anticipated effectiveness, and clinical acceptability. FITTER provides a clinician-facing approach integrating clinical and wearable data, guidance, and explicit safety constraints.
We study the problem of average reward Multi-Agent Reinforcement Learning (MARL) where agents interact within a network. Each agent in the network conducts local updates with information within its $k$-hop neighborhood and collaboratively maximizes the overall reward of the entire network. We first provide impossibility results in achieving convergence to the global optimal joint policies in our setting. These impossibility results highlight the challenges of decentralized learning with local information in multi-agent systems, namely the issues of multiagency, where each agent independently optimizes its policy, and partial observability, where agents have limited visibility into the global state. Given these challenges which indicate that decentralized policy optimization can generally be certified only up to stationarity, we provide finite-sample convergence guarantees for a decentralized actor-critic algorithm with linear function approximation that converges to an approximate stationary point with small gradient norm. To overcome such impossibility results, we further show that adding fixed-state entropy regularization reshapes the objective landscape which leads to even stronger global convergence guarantees for our proposed actor-critic algorithm.
Web navigation agents built on open-weight language models fail often and fail late, with most of the tokens spent after the trajectory has become unrecoverable. Recent work has shown that early termination is a viable cost-reduction strategy, but existing approaches produce opaque termination decisions that do not support diagnosis or human oversight. In this work we apply closed sequential pattern mining (BIDE+) to K-step prefixes of agent execution traces to produce a small, human-reviewable failure-signature library that organizes into a four-category failure taxonomy with associated repair recommendations. We use a multi-variant evaluation protocol that explicitly removes contamination artifacts (zero-step crashes and trivially separable single-step successes) so that reported detection accuracy reflects behavioral discrimination rather than trace-length distributions. We evaluate our methodology on 1,544 MiniWoB++ traces collected from three open-weight language models, achieving the best F1 at K=3 on the Exclude-errors configuration across eight methods (0.717), recovering 88% of test-set failures within three steps, and supporting an early-termination policy that saves 26.3% of tokens at 92% precision.
Long-horizon multi-agent systems suffer from three tightly coupled failures: task drift, role drift, and state staleness. We test the hypothesis that these share a common representational cause: agent hidden states move away from the directions encoding the active task, assigned role, and current shared state. A pilot study over 14,832 annotated turns supports this: drifted turns collapse near-uniformly across all three anchor subspaces (pairwise r = 0.72-0.78). Existing methods address these failures separately, operating at the surface-text level or treating control directions independently. We introduce ATLAS (Algebraic Task-role Locking with Adaptive Spectral Memory), a training-free intervention acting on hidden states before a token is generated. ATLAS builds a positive-semidefinite anchor kernel over task, role, and state subspaces and steers hidden states toward their shared high-coherence eigendirections; a low-rank Gram decomposition keeps this tractable. Across long-horizon memory, state maintenance, tool use, least-privilege coordination, and embodied stress tests, ATLAS outperforms prompting, retrieval, memory, and activation-steering baselines. Against A-MEM it improves memory macro-average accuracy by up to 5.7 points and reduces write/read failures by up to 31.7%/24.8%; against MemoryArena-Agent it gains up to 4.8 points. It gains 10.7-12.1 points under perturbation, reaches 93.5% role consistency, and transfers to a 72B backbone (macro-average 61.0 vs. 56.2). Ablating the joint task-role-state span costs 7.2 points against 0.8 for a matched-rank random span, indicating these directions are functionally implicated, not incidental; supplying them by prompt or retrieval recovers 4.3 points less. ATLAS is therefore a representation-level controller for open-weight multi-agent systems, complementary to output-level protocols for black-box agents.
Multi-agent LLM systems assign different responsibilities to different agents: one plans, another retrieves evidence, another verifies, another executes. This division of labor is only meaningful if each agent stays within the functions it is authorized to perform. Over many turns, however, an agent can produce a locally reasonable message that exercises authority belonging to another role: a verifier that begins planning, a retriever that asserts unsupported conclusions, an executor that changes state no one approved. We formalize this as role drift, a turn-level breach of an agent's role contract. We introduce Agent Trajectory Control (ATC), which makes each role's authority explicit as a contract and enforces it at the point where a message would enter the shared conversation. ATC scores a proposed output for out-of-role deviation, leakage into the functions of other roles, impermissible speech acts, and logical contract breaches, then computes a leakage-regularized target that constrains regeneration; the revised message is re-checked before admission. Enforcement acts on the message rather than the generator, so ATC governs agents whose internal representations are unavailable. Across homogeneous and heterogeneous teams, ATC improves task performance and role consistency while lowering role-drift energy relative to strong baselines spanning prompting, memory, workflow control, and activation editing, with the largest gains under explicit role-confusion stress tests and in larger, more diverse teams.
We propose goal-driven self-recursive optical research in which agents use physical evidence to revise the hardware, software, models, and protocols used to pursue a scientific goal. The framework can be instantiated with different stimulus systems and measurement devices. We formalize its updates and derive a relation between physical attainability, command access, and model approximation error. We demonstrate the concept in an optical see-through color-matching case study using an iPad, RayNeo X3 glasses, and a TOP 300 probe coupled to a CAS140D spectroradiometer, both from Instrument Systems. A revised glasses application adds USB-controlled RGB holds and frame acknowledgements, keeping model-generated colors displayed during spectral acquisition. The interface passes 12 live control checks. Spectral feedback reduces one target color difference from 19.756 to 1.211 {\Delta}E_76^*; all five targets improve in a separate comparison. These measurements demonstrate the concept in one configuration. The resulting software and protocols remain available for subsequent investigations.
Large language model (LLM) assistants are increasingly proposed for regulatory affairs, yet their reliability in regulatory tasks remains unclear. We introduce the EU AI Act Q&A Benchmark, an expert-curated benchmark of 110 open-ended questions about the EU AI Act (Regulation (EU) 2024/1689). Each question comes with an exemplary answer, question-specific correctness criteria, and expected references. Evaluation measures answer correctness, reference quality, conciseness, tone, and latency, with a multi-turn ``hard mode'' testing responses to simulated user pushback. We also present the results of the 2026 EU AI Act Q&A Challenge, based on the benchmark, where three off-the-shelf baselines and five purpose-built assistants (from four commercial developers and one academic entrant) were tested. Only two of the five submitted assistants consistently outperformed the baselines; one achieved high scores across all evaluated metrics. These results show that specialist development alone does not guarantee better performance and highlight the critical importance of LLM assistant evaluation in regulatory affairs. The benchmark code is openly available at https://github.com/regenold-GmbH/eu-ai-act-benchmark-2026/.
The deployment of AI agents in multi-agent settings enables inter-agent influence, whereby agents can strategically steer each other's behaviour towards an intended outcome. Such capabilities pose novel risks, as malicious agents could direct others towards harmful actions. In this work we investigate three such capabilities - persuasion, deception, and coercion - across five realistic evaluation environments and a variety of agents instantiated with frontier language models. We observed significant inter-agent influence capabilities; in oversight environments, all tested models shifted overseer decisions from rejection to approval through persuasion, deception, or coercion. We also observed successful influence in non-hierarchical 'peer-to-peer' settings through redirection of a peer's safety research trajectory. As multi-agent deployments become increasingly commonplace, these results point to a pressing need for work on mitigating the risks from inter-agent influence. Code and data are available at https://github.com/Cooperative-AI-Foundation/inter-agent-influence.
We study cooperative multi-agent reinforcement learning with decoupled dynamics and a monotone submodular reward function over joint trajectories. Due to the non-additive reward, an optimal policy may depend on the history of all agents. This dependence makes exact optimization exponential in the horizon and the number of agents. To overcome this challenge while retaining theoretical guarantees, we introduce pre-window curvature $c_m$, which quantifies how states visited more than $m$ steps earlier reduce current marginal gains. Using this curvature to control the error from restricting the policy of each agent to depend only on its last $m+1$ states, we propose a greedy algorithm that exploits the decoupled dynamics to optimize local policies sequentially. For fixed $m$, the algorithm achieves a $\frac{1-c_m}{2-c_m}$ approximation guarantee up to estimation error, and its computation time is polynomial in the number of agents and the horizon. We recover the known $1/2$-factor approximation for time-additive rewards and obtain an approximation factor no smaller than the known total-curvature bound for a single agent. We formulate multi-agent traffic monitoring as an example of this framework and evaluate our algorithm on it.
Multi-agent systems offer significant advantages in terms of flexibility and redundancy, enabling the efficient distribution of complex tasks among multiple robots. However, their deployment requires advanced control strategies to ensure optimal cooperation between autonomous agents and human operators. We propose a modification of the global connectivity maintenance algorithm to incorporate measurements taken in agent's local frame, using sensors with limited fields of view. This algorithm, responsible for the autonomous behavior of the multi-robot system, is combined with different adaptive supervision strategies, allowing the user to exert control at varying scales over the entire group. (i) Single Agent Control (S): The operator directly controls a single robot, (ii) Pinning Control (P): The operator imposes constraints on multiple robots to influence the group, (iii) Centroid Control (C): The operator acts on the system's center of mass to steer the entire fleet. In conjunction with the connectivity maintenance algorithm, these methods ensure compliance with inter-agent constraints while providing haptic feedback to the user regarding the system's connectivity state. The effectiveness of these approaches was evaluated through a user study, comparing performance with and without haptic feedback across multiple scenarios tailored to the different control modes.