Passes Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development

Agent systems often decompose a task across multiple roles, but these roles are typically specified by prompts rather than enforced by access controls. Without enforcement, a team pass rate can mask whether agents actually coordinated or whether one role effectively did another role's work. We present TeamBench, a benchmark with 851 task templates and 931 seeded instances for evaluating agent coordination under operating system-enforced role separation. TeamBench separates specification access, workspace editing, and final certification across Planner, Executor, and Verifier roles, so that no role can read the full requirements, modify the workspace, and certify the final answer. Prompt-only and sandbox-enforced teams reach statistically indistinguishable pass rates, but prompt-only runs produce 3.6 times more cases where the verifier attempts to edit the executor's code. Verifiers approve 49% of submissions that fail the deterministic grader, and removing the verifier improves mean partial score in the ablation. Team value is also conditional. Teams benefit when single agents struggle, but hurt when single agents already perform well. A 40-session human study under the same role separation shows that our benchmark exposes interaction patterns that pass rate misses. Solo participants work through the task directly, human participants paired with agents often collapse into quick approval, and human teams spend more effort coordinating missing information across roles.

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly corrupted, and existing outcome-based evaluations are blind to such multi-hop process failures. To make these vulnerabilities measurable before deployment, we introduce AgentCollabBench, a diagnostic benchmark of 900 human-validated tasks spanning software engineering, DevOps, and data engineering. Each task isolates one of four behavioral risks: instruction decay (does a constraint survive peer pressure?), false-belief contagion (does a falsehood spread through consensus?), context leakage (does information bleed between tasks?), and tracer durability (does marked data reach the final agent?). Evaluating four modern LLMs (GPT 4.1 mini, Gemini 2.5 Flash Lite, Qwen-3.5-35B-A3B, and Llama 3.1 8B Instruct), we expose model-specific vulnerability profiles invisible to outcome-only evaluation; Qwen-3.5-35B-A3B, for example, leads on tracer durability and instruction stability, while GPT 4.1 mini leads on leakage containment and false-belief resistance. Beyond per-model differences, communication topology emerges as a primary risk factor that explains 7-40% of the variance in multi-hop information survival. The effect traces to a synthesis bottleneck specific to converging-DAG nodes: an agent weighing competing parent inputs discards constraints carried by a minority branch, a bottleneck structurally absent from linear chains. AgentCollabBench demonstrates that suboptimal topology can silently erase the safeguards of highly capable models, arguing that multi-agent reliability is fundamentally a structural problem and that scaling model intelligence alone is no substitute for architecture.

Large Language Models (LLMs) are increasingly applied to software engineering (SE), yet their potential for autonomous, role-oriented collaboration remains largely underexplored. Understanding how multiple LLM-based agents coordinate, maintain role alignment, and converge on solutions is critical for SE, as naively allowing agents to interact does not reliably lead to correct or stable outcomes. Recent empirical studies show that unstructured or poorly understood interaction dynamics can result in error propagation, premature consensus on incorrect solutions, or prolonged disagreement that prevents convergence, even when correct partial solutions are present early in the interaction. As an initial step towards addressing this underexplored area, we undertake a systematic analysis of conversations between two agents, a Designer and a Programmer across 12 model combinations from 7 open-source LLMs (Gemma 2, Gemma 3, LLaMA 3.2, LLaMA 3.3, DeepSeek-R1, MiniCPM, and Qwen3). Our systematic approach reveals three key dimensions of multi-agent interaction: efficiency (the speed and stability of convergence), consistency (the degree of role alignment visualized by BLEU and ROUGE), and effectiveness (the extent of compilation success and error resolution). Results show that the DeepSeek-R1:DeepSeek-R1 pair was unique in converging to the correct solution from the very first iteration and sustaining it consistently to the final iteration, while LLaMA 3.2:LLaMA 3.2 and Qwen3:Qwen3 demonstrated strong Designer:Programmer role alignment despite of diverging from the correct solution. The other pairs deviated from the task, never to converge to a result. These findings advance understanding of agentic programming and highlight the need for further research on understanding and calibrating convergence and stop conditions essential for future autonomous SE.