Multi-Agent Collaboration

Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, while search, reasoning, and coding are handled through asynchronous delegation. A duplex model supports continuous listening and speaking, but complex reasoning and tool use may exceed its capabilities. A coding agent can plan and execute extended tasks, but its sequential interface is a poor fit for live conversation. Combining them requires a harness that coordinates task acceptance, progress, cancellation, replacement, and result delivery while keeping the conversation responsive. Existing harnesses often rely on coupled heuristics, making them difficult to improve systematically from evidence. We present DuplexAgent, a full-duplex collaboration system whose harness expresses this workflow as six editable modules, and Duplex-Harness-RSI, a closed loop that revises them from interaction traces. A simulator automatically generates timed test conversations, runs the system, and produces failure traces that identify the collaboration modules requiring repair. Reasoning LLMs and coding agents in the delegation pool also serve the improvement loop: the Exam Planner selects the next tests from observed weaknesses and the repair archive, and the Harness Editor proposes targeted module changes. The capabilities that serve the user thus also improve the system's coordination. Experiments on intelligence, agentic, and duplex benchmarks show that DuplexAgent combines continuous interaction with difficult reasoning and complex task execution, achieving stronger spoken-knowledge and executable-tool scores than the compared delegated systems while maintaining strong interruption response. A harness ablation further shows that this modular, verifiable loop outperforms the initial harness and repeated editing that lacks its diagnosis and repair archive.

LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple agents should yield near-linear speedups. Yet existing parallel multi-agent systems often run slower than a single-agent baseline. We attribute this gap to two hidden costs that parallel execution incurs but a serial agent avoids. First, there is a re-exploration cost: redundant effort spent by parallel workers reconstructing context that the orchestrator already possesses, such as prior decisions, that would otherwise be inherited implicitly in a serial execution. Second, there is an alignment cost: the overhead required to reconcile inconsistencies across independently generated outputs. We thus derive a principled decision criterion: a layer should be parallelized only when its critical-path cost, plus re-exploration and alignment overheads, is lower than the corresponding serial cost. While this criterion is naturally expressed in wall-clock time, we observe that LLMs are poorly calibrated when asked to estimate task duration. To address this, we instead measure cost in predicted output tokens, which we empirically find LLMs can estimate substantially more reliably than wall-clock time. Building on this token-based criterion, we propose SquidAgent. It estimates all token budgets in a single planning step, forks each worker directly from the orchestrator's session to eliminate re-exploration cost, and replaces post-hoc reconciliation with a pre-generated shared convention block that converts alignment into a bounded upfront cost. A deterministic scheduler then applies the criterion layer by layer. Empirically, SquidAgent achieves a 2.2$\times$ mean throughput improvement and a 2.6$\times$ mean wall-time speedup over Claude Code, and a 2.0$\times$ throughput improvement over the strongest multi-agent baseline.

Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative problem solving among specialized agents. However, existing MAS frameworks tightly couple task reasoning with coordination operations, including task selection, role assignment, message routing, and context management. As interactions grow, using powerful LLMs for these bounded control decisions introduces substantial token overhead and latency, limiting the scalability of agentic Web services. In this paper, we investigate whether coordination can be decoupled from expensive reasoning without compromising collaborative performance. We propose S1-MAS, a token-efficient multi-agent framework based on System One-guided computational division of labor. S1-MAS assigns bounded coordination decisions to lightweight System One models while reserving open-ended reasoning for capable LLM workers. Specifically, a lightweight controller selects inspection conditions, chooses subsequent tasks, and determines termination, while a compact reader retrieves condition-relevant evidence from authorized sources to support these decisions. Through a decision-evidence loop, selected tasks dynamically determine worker roles and source access, enabling adaptive collaboration without task-specific training. Extensive experiments on seven diverse benchmarks demonstrate that S1-MAS achieves superior accuracy while substantially reducing the inference cost. Across individual comparisons with AgentVerse, DyLAN, and SelfOrg on seven benchmarks, S1-MAS reduces GPT-4o token consumption by 44.9%-97.2% and measured end-to-end latency by 37.8%-93.0%. These results highlight its potential for scalable and cost-effective agentic Web applications.

While medical multimodal large language models (Med-MLLMs) advance medical visual question answering (VQA), existing clinical workflow-inspired multi-agent frameworks suffer from interaction patterns and excessive computational overhead caused by redundant communication topologies. 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. Specifically, we first formulate the diagnostic process as a heterogeneous communication graph, where nodes represent specialist agents from various departments and edges capture intra- and inter-departmental interactions. 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 question via reinforcement learning-driven topological optimization, and (2) Heterogeneous Edge Sparsification, which selectively retains only the most diagnostically salient intra- and inter-departmental connections by jointly optimizing task performance and topological complexity. Extensive medical VQA experiments under full-set and few-shot training settings prove MedPrune surpasses multi-agent baselines and boosts token efficiency with strong adversarial robustness.

AI agents can each make locally valid decisions yet jointly produce an invalid result. We call this the global coherence problem: a failure of shared state, not merely of model intelligence. Our Observation-Aliasing Impossibility Theorem gives the exact boundary. A policy can guarantee a valid action exactly when all worlds producing the same observation share an admissible action. If k indistinguishable worlds require pairwise-disjoint actions, the best randomized worst-case success is 1/k; more reasoning, roles, messages, or samples cannot recover the missing distinction. A stronger model can reason better within its context, but it cannot see beyond it. We then give local-to-global runtime semantics X = (H, C, G, F; D): topology H records overlapping scopes; category C governs state-changing actions; groupoid G retains reversible translations; sheaf F tests whether local views glue into one world; and minimal history D keeps only distinctions that alter legal futures. Models propose; the harness owns shared state and governs commit. Nine studies test both the failure and its boundary. On a controlled revision benchmark, the same frontier model scores 40/40 when the deciding event is visible; when it is hidden, tested arms score 12--17/40, consistent with chance (1/3); restoring one authoritative fact returns 40/40. On TeamBench, ordinary teams exceed a shared budget in 5/5 runs, a visible live count leaves 4/5 violations, and commit enforcement leaves 0/5. In tau2-bench Telecom, current-state checks score 0.07 after silent reverts, while the harness scores 1.00. Where a conventional solver already owns the complete relevant state, it ties the harness as predicted. The counterintuitive conclusion is that local intelligence cannot substitute for missing global state.

Multi-agent systems are often judged by whether they reach the correct answer. This can miss a distinct failure: collaboration may leave behind a corrupted information state even when the immediate decision is correct. We call this an off-query failure. To study this failure in collaborative decision support, we introduce OffQuery, which separately evaluates evidence verification (T1), shared-state reconstruction (T2), and task resolution (T3) in two representative high-stakes settings: healthcare and disaster response. Across GPT, Gemini, and Qwen models, standard collaboration shows much stronger task performance than state reliability. Averaged over 21 model--setting combinations, task resolution reaches 64.7%, while evidence verification and state reconstruction reach only 14.3% and 43.1%. We trace this gap to selective information use: current queries often bypass corrupted facts, which become consequential when later tasks require them. We further introduce ReGround, which resolves conflicting evidence, verifies shared facts, reconstructs a trusted state, and reasons over that state. Across seven models from three families, ReGround improves all three capabilities in every evaluated setting, with average relative gains of 309.0%, 82.9%, and 17.6% on T1, T2, and T3. Reliable collaboration therefore requires both a correct decision and a reliable shared state for future reasoning.

Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate specialized agents to work together on these tasks. Recent methods train LLMs to construct better workflows from execution outcomes, but they optimize only the workflow generator, while the other agents that build or execute each workflow remain fixed even though every outcome depends on all of them. However, extending training beyond the generator is challenging: the agents are coupled, and a workflow's outcome is a single sparse score that cannot tell which agent causes a failure. We propose FloWright, which leverages the workflow as a harness to optimize workflows. By introducing a hierarchical, structure-aware reward paradigm, FloWright enables one role to self-evolve and two or more roles to co-evolve, with no additional models, labels, or executions. Considering the limitation that workflows are commonly trained and evaluated on data that a single agent can already handle, we further propose DataWright, an adaptive data hardening approach that converts existing datasets into workflow-level tasks with increased difficulty. Across document, slide, chart, code, math, and finance tasks, small open models trained with FloWright achieve improved performance by up to $+7.41\%$, with co-evolving ($+5.03\%$) more roles gaining more than optimizing one of them alone ($+2.83\%$). Our project page: https://xhguo7.github.io/FloWright/.

We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often insufficient for open problems that require exploring multiple competing conjectures, overcoming subtle technical obstructions, and retaining intermediate progress over a long horizon. Cogentic addresses these challenges through an iterative prove--verify loop in which an orchestrator allocates a population of independent provers across distinct proof directions, subjects their output to adversarial verification by several specialized components, and promotes confirmed intermediate results into a persistent verified ledger that later rounds build on. The harness is designed to be able to solve research-level math and theoretical computer science problems. Using Gemini as the base model, Cogentic produced novel results on five open problems across online learning, auction theory, and mechanism design. Each result was independently verified by domain experts and is developed in full in companion papers. We list these results, and new ones as they are verified, at https://sites.google.com/view/cogentic .

Multi-agent collaboration lets large language models (LLMs) improve question answering through deliberation and feedback. Yet shared discussion couples correction with exposure to the same mistakes, which can erode the diversity needed for voting. Self-consistency offers sampling diversity without feedback, while single-pair Actor-Critic collaboration refines only one candidate. We introduce SEPAL, which assigns three private Actor-Critic teams to direct reasoning, evidence grounding, and verification. Role-specific training gives the teams different reasoning objectives beyond sampling variation. Each Critic guides revisions within its own team, preventing feedback from carrying errors across candidates. Once revision ends, majority voting combines only the final answers, keeping the reasoning histories separate until the decision. Across five open-weight backbones and five question-answering benchmarks, SEPAL improves mean accuracy by 1.81 percentage points over a matched single Actor-Critic pair, with improvements across all five backbones. Code is available at https://github.com/zhansan114514/SEPAL.

Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contributions that are admissible in isolation can jointly enable a prohibited use. Blocking every sensitive action avoids disclosure but defeats the purpose of collaboration. We introduce authorization-paired evaluation, which makes blocking prohibited uses and completing required authorized uses a joint success criterion, and FlowReview, a framework connecting object resolution, permission ranking, and deterministic enforcement. In controlled composition experiments, reviewing combined artifacts reduces the denied-commit rate from 86.0% to zero with no loss of authorized supply. Our findings show that preserving information and lineage alone does not ensure correct permission attribution. Object identity and permission must remain connected to execution through components whose outputs can be verified. Together, these findings establish a system-level requirement for multi-agent safety: govern composed information flows while preserving the authorized capabilities that make collaboration useful.

Recursive self-improvement (RSI) lets a system improve from its own outcomes; in LLM-based multi-agent systems, Agents refine one another within a task, and outcomes improve how they collaborate across tasks. However, existing multi-agent collaboration leaves this loop open: collaboration is pre-defined at the operator level, topology-only learning keeps verbatim exchange that propagates errors, and reward maximization on a system's own outcomes concentrates on a few teams. To address these challenges, we propose CollabFlow, an RSI system of Learned Agent Collaboration: a trainable Collab-Director constructs teams of complete Agents, a frozen executor runs them, and each round's outcomes retrain the director. Within each round, the edges of a collaboration graph carry protocols of Evidence-Conditioned Communication: a receiver adopts a differing answer only when the sender's evidence is stronger by a margin, so the director learns who communicates and how. Across rounds, we further propose Collaborative Trajectory Balance (CTB), a flow-based objective that credits each team once across its construction orders and targets a reward-proportional distribution over teams, so several good teams stay in play. We also bound how far this self-generated target moves between rounds, which shrinks as records accumulate. On twelve datasets, CollabFlow outperforms all baselines and keeps improving across rounds. Code is available at https://anonymous.4open.science/r/CollabFlow-631E.

Stronger AI agents do not automatically produce better organizations: teams must also learn which work arrangements to retain and when to reconsider them. We propose a modeling specification for recursive organization improvement and evaluate it through an executable checker, a public-record mapping, and controlled simulation. The specification connects actor-visible histories, organizational memory, decision rights, and evidence-carrying change contracts. The mechanism study crosses six decision rules, three memory conditions, and three task environments under fixed resource ceilings. In a stationary environment, cumulative evidence raises balanced evaluation's normalized net value per task from 0.45224 to 0.48007. Repeated reassessment's disadvantage relative to this comparator falls from 0.01702 with reset evidence to 0.00007 with cumulative evidence. A reversal of the best workflow reveals the opposite cost: indefinite retention delays adaptation, while a finite window restores eventual performance at a transition cost. In exploratory controls, matching trial acquisition and label reuse reduces the apparent reassessment gain from 0.00607 to 0.00191. Program replacement adds no stable benefit across the tested reversal times. The study identifies evidence acquisition, reuse, and timely updating as mechanisms that must be separated from evaluator replacement when assessing organizational improvement.

Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configured organizations are followed faithfully, whereas reality differs. This behavioral gap, combined with differences in underlying system components, prevents clear attribution of observed gains. To this end, we introduce OpenCollab, a multi-agent coding framework that provides a unified infrastructure for programmable collaboration and controllable runtime. Specifically, OpenCollab unifies organization design, enforces experimental control on a shared runtime, and tracks execution through fine-grained event streams. On this basis, we define Adherence to quantify whether the declared organization is actually realized. 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%. Furthermore, extensive agentic coding benchmarks show that a two-coder workflow built on OpenCollab establishes new SOTA performance compared to the mainstream harnesses such as Mini-SWE-agent, Codex CLI, and Claude Code, showing that a well-designed organization can outperform strong existing harnesses, while OpenCollab's single-agent configuration uses the fewest tokens across all evaluated suites. OpenCollab establishes a unified multi-agent infrastructure for easy programmable collaboration and controlled causal evaluation.

Generative modeling is widely used for producing diverse objects from complex, multimodal distributions. However, its expressivity does not, in general, come with formal guarantees that the generated objects satisfy hard constraints or requirements. In multi-agent generation, this problem becomes more challenging because a hard requirement can depend on multiple agents, while each agent may need to determine its own guidance input without relying on the simultaneously computed guidance inputs of other agents. To this end, we introduce DeGG-Flow, a general framework for multi-agent flow matching with decoupled generative guidance. By representing the generative process as a control-affine dynamical system, we develop guidance conditions for two classes of coupled requirements: shared requirements whose satisfaction depends on multiple agents together, and private requirements associated with each individual agent dependent on its neighbors. For both classes, we establish feasibility conditions and finite-horizon convergence guarantees. We further derive a Wasserstein bound that characterizes the distributional deviation induced by the guidance. We demonstrate DeGG-Flow on multi-robot collaboration for crossing a spatial gap by reconfiguring the environment, and on multi-object scene generation with affordance requirements. Across both applications, DeGG-Flow directly generates objects that satisfy all corresponding hard requirements, including at team sizes unseen during training.

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 delimit private and selectively shared memory. Existing methods can jointly optimize agent and communication structures, yet such optimization does not by itself require responsibility, handoff, and memory boundaries to remain consistent with task dependencies. We term this requirement topological coherence. We introduce TOCOMAS, a Topology-Coherent Multi-Agent System. TOCOMAS grounds a task graph in tool interfaces, organizes compatible task nodes into reusable responsibility domains, and derives dependency-induced and profile-conditioned collaboration together with boundary-regulated memory visibility. During online self-evolution, TOCOMAS proposes coupled changes to agent, collaboration, and memory policies, retaining for subsequent tasks only candidates that satisfy structural constraints and improve evaluated reward. Across BBEH, WorkBench, SWE-Bench-Verified, and CoMemBench, TOCOMAS improves task success over baselines across backbones. CoMemBench also shows gains over the self-evolving baseline in verified progress, handoffs, and memory isolation.

LLM-based multi-agent systems (MAS) increasingly use latent collaboration to avoid the information loss and repeated encoding-decoding overhead of natural-language communication. However, directly forwarding all sender latents makes the receiver-side context scale with both the number of agents and the reasoning length, increasing computation, memory usage, and collaboration latency. A natural solution is latent compression. But we find that cross-agent redundancy remains unresolved in existing latent compression approaches, which typically compress each sender independently and then concatenate the results. We propose LatCom, a cross-agent latent compression framework for efficient multi-agent latent collaboration. LatCom maps multiple sender latents into a fixed number of receiver-readable and task-relevant slots. Rather than reconstructing all sender hidden states, it optimizes the compressed latents for receiver-side task utility. LatCom trains the compressor in two stages: single-sender readability learning first establishes a latent interface interpretable by the frozen receiver, and multi-sender fusion learning then trains the compressor to fuse complementary evidence and remove redundancy across agents. 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.

Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful information or an incorrect answer that causes a downstream agent to override a correct answer supported by its own evidence. Prior work has not clearly separated the benefits of communication from the damage caused by incorrect messages. We study this problem with controlled experiments across five benchmarks and five receivers, keeping the downstream task and evidence fixed while comparing answers under three conditions: no message, the upstream agent's original message, or a message with the opposite conclusion. Our experiments reveal three key findings. First, messages often help when the downstream agent would otherwise answer incorrectly. Second, messages can also hurt: when the downstream agent would answer correctly without a message, an incorrect upstream message changes the answer in up to 32% of cases. Third, in 94% of audited harmful cases, the downstream agent copies the upstream's specific wrong answer--a pattern we term answer substitution. Removing unreliable messages recovers part of the lost accuracy, suggesting that communication should be selective based on upstream reliability and the evidence already available to the downstream agent.

Can a population of neural networks develop a useful division of labor without a shared gate or gradients between agents? We study a setting where each network has its own weights, trains independently on the same heterogeneous data, and can ask another agent for help through a forward pass. Unlike mixtures of experts, where a jointly trained gate assigns inputs to experts, specialization here must emerge without central control. We test this in a small scale proxy for predictive visual pretraining. Initially identical agents are finetuned on an unlabeled mixture of six visual domains using masked prediction of frozen DINOv3 features. We measure specialization by asking whether the best agent for an input aligns with its latent domain, and utilization by asking whether responsibility is distributed across agents. We progressively remove central control, ending with DISCO (DIStributed COllaboration) where each agent locally selects a helper, reads its internal state through a gradient free channel, and rewards its router only for the improvement that help provides. Specialization emerges and is useful. Randomly routed populations underperform a single generalist, while semantically routed populations outperform it, showing that specialization rather than population size drives the gain. Specialization persists without a central router, and gradient free communication lets nonexperts exploit emergent expertise. In DISCO, a random agent helped by the expert matches the solo generalist, while experts surpass it, including on data outside the specialization mixture. Local routers select the emergent expert for 98% of inputs. These effects persist across population size, model capacity, data imbalance, and finetuning seeds, providing measurable evidence for the dynamics needed by decentralized predictive pretraining.

Multi-agent LLM systems are increasingly structured like organizations, with roles, critics and shared memory, yet they are evaluated on tasks that last minutes. We ask how such an organization behaves when the ground it stands on keeps moving. Frontier Autolab is a long-horizon testbed in which one simulated firm, voiced by sixteen role personas and a dedicated Red Team, must re-found itself in nine technology eras from 1990 to 2040. Each era is temporally gated: the firm decides from a dated briefing, a historian-judge then reveals what happened and scores the decision on a five-dimension rubric, and lessons enter a persistent Playbook. Six eras are scored against history, one against the live market and two are open forecasts. Across four trajectories (36 era decisions, 180 subscores) we find a consistent foresight-commitment gap: in all 24 historically scored eras the judge rated the firm's recognition of the coming shift above its choice of where to build (mean gap 1.9 points on a 10-point scale), because boards chose the layer their existing assets could reach. Organizational design shaped long-run character. A Red Team armed with numeric kill gates produced fifty years of gated pilots and no product, and the rubric rated this firm highest; firms whose memory stored market-structure lessons pivoted every era, while a firm whose memory stored only validation procedure kept one method throughout. We also show why such results are hard to trust. Scores rise across eras in every run while the judge's own hindsight subscore falls (within-run r = -0.58), so apparent learning is confounded with recall of history, and we trace further distortions to self-judging, briefing selection and score aggregation. We release all records and an API harness, and specify fictional and post-cutoff eras that would turn the testbed into a benchmark.

As autonomous systems and embodied intelligence enter the dynamic physical world, multi-agent collaboration calls for a paradigm shift in communication design. However, existing communication paradigms overlook that agents form action understanding from their own states, environmental observations, and collaboration relations through a process that evolves as a task unfolds. Consequently, reliable bit delivery, general semantic recovery, or single-task utility optimization alone cannot ensure that heterogeneous agents form coordinated actions compatible with their own conditions from shared information during task execution. To address this gap, this paper proposes embodied semantic communication (ESC) as a paradigm that transforms information transmission into action-oriented semantic interaction. Specifically, ESC characterizes how an explicit communication link can encapsulate multimodal perceptual states, intrinsic hardware capabilities, and collaborative intents into unified actionable semantic representations, thereby enabling heterogeneous receiving agents to parse, align, and ground them in local motor control. This paper clarifies the conceptual boundary, system characteristics, and environment-constrained technical pathways of ESC. It maps the underlying mathematical tools, including semantic information theory, world models, and multi-agent decision theory. Finally, this paper summarizes key open challenges, including measurable semantic reliability, ambiguity-triggered interaction under dynamic environments and tasks, and bandwidth-adaptive semantic transmission, outlining a roadmap for collective embodied networks.

Large Language Model (LLM)-based agents promise to automate scientific discovery, yet exploring the vast hypothesis space remains costly. Existing principle-evolution methods accelerate this loop, but operate sequentially, which caps exploration breadth and wastes wall-clock time on challenging problems. To address this, we formulate collaborative scientific discovery as evidence transfer between parallel principle-evolution branches. We present COEVOLVE, which realizes this transfer through a coordination core over parallel branches. By integrating value-of-information-gated routing and context-discounted likelihood injection, COEVOLVE enables branches to collaborate through shared measurements while keeping their principle posteriors separate. Across six scientific-discovery tasks under a matched evaluation budget, COEVOLVE attains a mean solution quality of 66.5% versus 57.0% for single-branch principle evolution, with a 1.80x mean wall-clock speedup on the GPT-5.6-Terra backbone; on five auto-research tasks delegated to an autonomous research harness, it is the only arm whose mean stays above the published SOTA anchor on every task. These results establish when evidence sharing accelerates parallel discovery and when transfer safeguards are necessary to limit negative or inert transfers

Many physical tasks in human environments require collaboration, from assisting a partner to jointly manipulating an object. Yet, existing humanoid benchmarks largely focus on single-humanoid skills and lack evaluation of multi-humanoid collaboration under egocentric visual observations. We introduce CoHuB (Collaborative Multi-Humanoid Benchmark), a simulation benchmark for multi-humanoid collaboration under egocentric visual observations. CoHuB provides 10 tasks, eight with two humanoids and two with three humanoids, spanning diverse collaboration patterns. We also provide synchronized demonstrations collected through a multi-operator VR teleoperation pipeline, in which each operator controls one humanoid from its egocentric view. Experiments with representative visuomotor policies reveal substantial challenges across different forms of coordinated perception and control. CoHuB provides a foundation for developing and evaluating multi-humanoid collaboration policies.

LLM-based multi-agent systems (MAS) have shown promise in complex problem solving. As MAS methods diversify, systematic evaluation becomes increasingly challenging. However, existing benchmarks largely focus on final outcomes, leaving unclear how collaboration gains arise, are preserved, or are lost. To address this limitation, we introduce MASTraceBench, a benchmark for diagnosing collaboration gains through proposal trajectories in MAS. Across six cooperative and competitive tasks, MASTraceBench tracks and grades proposal trajectories and provides a multi-layer metric suite covering Task Score, Collaboration Gain, proposal-trajectory indicators, and Token Cost. Using MASTraceBench, we systematically compare representative MAS methods not only by final performance, but also by how agent proposals evolve and are aggregated into the final answer. This analysis reveals a recurring pattern: final MAS answers rarely surpass the strongest initial proposal; interaction often lifts initially weaker proposals toward it, while strong initial proposals are seldom further improved and may regress. To reduce this risk, we propose CLEARS, which replaces whole-proposal exchange with claim-level evaluation across agents to guide reliable synthesis. CLEARS more often preserves or improves upon the strongest initial proposal and achieves the highest Collaboration Gain on five of the six tasks.

Multi-agent systems (MAS) split a task across specialized roles and are promising on complex tasks, yet a prevailing approach relies on inference-time orchestration alone. General-purpose APIs are costly and hard to customize, while small models with role prompts rarely develop stable role competence or reliable collaboration, so post-training a MAS jointly is central. Most attempts use reinforcement learning, whose team-level reward leaves undetermined which step of which agent brought about the outcome, while local rewards need redesigning per task. On-policy distillation (OPD) gives token-level teacher supervision on trajectories the student samples, a denser signal needing no local reward, yet is underexplored for the interdependent agents of a MAS. Two difficulties arise: building complementary specialization from a judgement of which role a behavior belongs to while preserving the knowledge all roles need, and turning cross-agent collaborative information into supervision OPD can exploit. We present MAS-OPD, where Role-Advantage Specialization defines the role advantage as the difference between the teacher signals under target and non-target role conditions, and Privileged Attribution for Coordination attributes an interaction conflict to its source and supplies it to the teacher alone as privileged information. Extensive experiments on code and mathematics benchmarks show that MAS-OPD attains the highest mean score at both student scales and leads the agents to develop clearer role specialization and more effective collaborative behavior.

As large language models advance, AI agents are moving beyond isolated, domain-specific tasks toward long-horizon, cross-domain workflows. This transition exposes two challenges: increasing harness complexity makes manual design difficult to scale, while tighter coupling to specific domains limits the generality of a single harness. The central question thus shifts from how to engineer a stronger harness for one domain to how to autonomously construct specialized harnesses, improve them through experience, and orchestrate them across domains. We introduce Raven, \emph{The Harness of Harnesses}, an open-source multi-agent ecosystem that automatically constructs and evolves modular harnesses for specific models and domains, treating each executable model--harness pair as a composable unit of intelligence. To support an \emph{All-Domain Collaboration Network}, its Host Agent decomposes goals, matches subtasks to specialized agents, coordinates execution dependencies, and integrates results, while a host archive and EverOS preserve experience across tasks and Skill Forge makes that experience available as reusable procedures. Our theory establishes sufficient conditions for such composition to expand reliable task coverage beyond that of the available individual agents under a shared resource budget. On complex and long-horizon tasks, Raven significantly outperforms the state-of-the-art agent systems, pushing the frontier of composable agentic intelligence.

Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to develop on the old version where existing tests become stale. A conversation can resolve the episode, but when the participants change, what makes the lesson continue to govern the team? We introduce Relic, which turns recurring collaboration failures into organization-owned, executable protocols. Members reflect on visible work, propose rules, and govern their adoption. Adopted protocols bind triggers, responsibilities, required evidence, and execution consequences to the runtime, while remaining open to revision and retirement. In one traced case, repeated integration friction produces an interface-review rule that governs later pull requests and is revised as work continues. Across 360 controlled runs over ten software workloads and three models, Relic raises complete-contract delivery from 14.06% to 19.76% (+5.71 percentage points) over a matched structured team without the protocol lifecycle, improving all four verified production endpoints in every model stratum. Under fresh-member transfer, behavioral correctness is 25.4% with no inherited protocol, 34.6% with the same rules provided as readable text, and 41.2% with executable bindings, a +6.5-point advantage over text alone. On the full CooperBench benchmark, after excluding 183 broken benchmark pairs, Relic achieves 371/469 (79.1%), establishing the best reported result among peer-structured systems. On the 47-pair same-model subset, Relic also exceeds Solo (28/47 vs. 26/47), reversing the coordination loss exhibited by the official peer baseline. Together, these results show how collaboration experience can become persistent organizational state that remains useful beyond the members who created it.

Multi-agent workflows require task-relevant information to be shared across agents, while irrelevant, stale, unverified, or incompatible information must remain isolated. We call this task-conditioned scope of information a collaborative memory boundary. Workflow topology determines which intermediate artifacts are applicable to which downstream workers and when they cease to be valid, thereby providing a structural stress dimension for sharing and isolation. Existing memory benchmarks primarily evaluate retention and retrieval, whereas multi-agent benchmarks emphasize coordination and end-to-end completion, leaving topology-conditioned memory boundaries largely unmeasured. We introduce CoMemBench, an execution-grounded benchmark for collaborative memory sharing and isolation across multi-agent workflow topologies. It constructs 800 composite workflows across four domains from source-grounded dependency graphs, with node-local specifications, verifiable artifact handoffs, native evaluators, and matched isolation challenges. CoMemBench measures workflow completion, verified node progress, required-handoff reliability, isolation robustness, and token cost. Experiments reveal a sharing-isolation trade-off: broader context improves information availability but can weaken isolation, while system rankings shift across topologies and artifact violations.

In open-ended problem solving, collaborators often rely on discussion to surface concerns, challenge perspectives, and refine shared work as it evolves. While AI agents are increasingly used as discussion partners, existing multi-agent systems place a heavy burden on users to initiate and carefully orchestrate the discussions. We present DocuTeam, a mixed-initiative multi-agent discussion system in which both users and agents can initiate and steer conversations. Agents monitor document changes to proactively start and redirect discussions as the work evolves, while users can flexibly shape the conversation or adopt agent ideas. In a within-subjects study (N=20), participants using DocuTeam produced outcomes rated significantly more novel, relevant, and specific than with a baseline without any increase in cognitive load. Rather than using agents for one-off idea sourcing, participants engaged in an iterative refinement loop in which document changes prompted agent reactions, which led users to revisit and further develop their work.

Humanoid robots require diverse embodied experiences to acquire complex loco-manipulation and collaborative skills. However, existing humanoid data pipelines primarily focus on individual agents, while physical multi-robot collaboration remains difficult to scale due to costly hardware, dedicated spaces, and repeated resets. In this work, we introduce MATE, a Multi-Agent virtual TEleoperation platform for humanoid collaboration data collection that enables multiple geographically distributed operators to simultaneously control whole-body humanoids in a shared physics-based environment. MATE removes the need for multiple physical robots and co-located operation while preserving physically coupled interactions among humanoids, objects, and environments. Using MATE, we construct a multi-humanoid collaboration dataset comprising 24.1 hours of coordinated behavior across 2,500 joint episodes and five long-horizon tasks, including object handover, relay delivery, environment interaction, and cooperative transport. To improve learning from these interaction-rich demonstrations, we introduce EAIS, an Execution-Aligned Interaction Sampling strategy that computes sampling signals within an execution-aligned prefix and prioritizes task-progressing and interaction-critical behaviors. We evaluate MATE with representative imitation learning and vision-language-action policies across diverse collaboration tasks. Experiments demonstrate efficient data collection, effective policy learning, and zero-shot transfer from virtual demonstrations to a physical humanoid without real-world fine-tuning. Project page: https://yerik-yu.github.io/MATE/

The rapid advancement of large language models and single-agent harnesses has reshaped the landscape of autonomous systems, raising a critical question of when multi-agent collaboration offers genuine value. As individual agent capabilities continue to scale, multi-agent collaboration faces diminishing returns while incurring growing context overhead. Through systematic analysis, we delineate the capability boundaries of multi-agent collaboration relative to single-agent alternatives, showing that it confers systematic benefits specifically in long-horizon tasks with sparse dependencies, while single-agent harnesses remain superior in tightly coupled, sequential workflows. Building on these insights, we propose SAIGE, a lightweight multi-agent collaboration mechanism based on Semantic-Aware Incremental Graph Evolution. SAIGE models collaboration as a dynamically evolving graph, where nodes are agent instances spawned on demand and edges encode semantic dependencies established through content-based information retrieval. Experiments on long-horizon, complex task benchmarks show that SAIGE achieves a favorable trade-off between context efficiency and task performance, and that scaling the agent pool or deepening the recursion level does not consistently improve outcomes. Our findings suggest that multi-agent superiority is bounded by task structure rather than universal, and that more agents do not necessarily make a system more intelligent.