cs.AINov 13, 2026

Aligning AI Teams

Authors: Siddarth Srinivasan, Morgan Jane Matthews, Jascha Sohl-Dickstein, Erik Jones

Organizations: Harvard University · Constellation Institute · Anthropic

Abstract

Previous work has shown that alignment training on individual LLM agents can fail to transfer to multi-agent settings. We investigate the underlying mechanisms for this failure, and explore interventions to preserve alignment transfer to multi-agent LLM teams. We focus on two software-engineering tasks (sepsis triage, a news recommender) and ten consulting-proposal generation tasks. We present four findings: (1) The single-vs-team safety gap does not show a clear trend with more capable models. We find that Anthropic's Mythos Preview shows the largest gap on one of our tasks but the smallest on another; (2) Many natural interventions, such as having agents critique each other's work or coordinate in a group chat, do not reliably bring agent teams back to single-agent alignment behavior; (3) diffusion of responsibility substantially accounts for the safety gap: agents in teams are less likely to proactively check for system-level safety failures and more likely to ignore, rationalize, or deflect responsibility for issues when they arise; (4) having a designated safety lead agent ensure system-level safety, and having a coordinator agent publish a safety specifications document are effective at restoring single-agent alignment. We also release magelab, a multi-agent LLM orchestration and experimentation framework. Our findings can help practitioners design agent teams that successfully preserve the behaviors expected of aligned individual agents.

Figures & tables

Appendix figures & tables37 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 26, 2026

Delegated Misalignment: How Multi-Agent Structures Amplify LLM Safety Risks

Large language models (LLMs) are increasingly deployed in multi-agent systems where a principal agent decomposes tasks and delegates them to subordinate agents that may invoke external tools. Safety alignment, however, is still evaluated almost exclusively under a single-agent threat model, treating safety as a property of the individual LLM. We show that this assumption breaks down: individual safety alignment fails to transfer to multi-agent settings. Two failure mechanisms emerge under delegation: responsibility diffusion on the principal side and role-bias compliance on the subordinate side, jointly converting language-level refusal into actionable harm. We refer to this phenomenon as delegated misalignment and study it through a three-condition protocol across 6 frontier LLMs on 49 hazardous tasks. Delegation amplifies end-to-end harm substantially: DeepSeek-V3.2's full-execution rate rises from 30.6% to 77.6% once delegation is introduced, and the same model behaves very differently across roles (GPT-5: 22.5% as a single agent vs.\ 61.2% as a subordinate). Ablations further show that standard single-layer defenses each fail on their own and can even backfire. We call on the community to move beyond per-model alignment and toward composite safety mechanisms before multi-agent LLM systems are deployed at scale.
May 1, 2026

TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination

Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines. We identify a structural failure mode in sequential fine-tuning of shared-context teams: updating one agent shifts the team's context distribution, and when subsequent updates are evaluated on cached rollouts, this mismatch compounds. We formalize this as the compounding occupancy shift and prove that stale-occupancy evaluation incurs a penalty that scales quadratically with the number of agents. In contrast, intermediate-occupancy evaluation reduces this to linear scaling. We propose TeamTR, a trust-region framework that resamples trajectories after each component update and enforces per-agent divergence control, yielding rigorous per-update and per-stage improvement lower bounds. Experiments show that TeamTR outperforms single-agent and sequential baselines with 7.1% on average, mitigates coordination regressions, and supports plug-and-play component replacement. Code is available at https://github.com/Yydc/TeamTR.
Nov 17, 2026

Bad Apples in the Kitchen: How LLM Teams Detect, Correct, and Calibrate Against Their Misaligned Members

What protects an LLM team when one teammate quietly goes wrong? Most multi-agent LLM work assumes cooperative partners and inspects chat between turns before acting. Real-time embodied cooperation does not allow this pause: chat runs alongside action, so a teammate whose words stay cooperative while behavior diverges can cause damage faster than the team can name what is happening. We study this case by injecting three theory-grounded misaligned agents into a custom four-player Overcooked environment, each stressing a different joint-action layer (speech-action mismatch, role invasion, and aggregate-progress disruption), and decompose robustness into three sequential gates of detection, correction, and calibration through a 3x4x2 design (n=720 episodes). Nearly all trolls are eventually named, but recovery follows only when attribution and situational diagnosis appear in the same utterance; direct source-attribution prompting improves the hardest case only by degrading the troll-free baseline by 37.5%. Robustness, then, depends less on detection alone than on whether team chat combines attribution with diagnosis in a single utterance, suggesting that sensitivity to misalignment should be targeted rather than uniformly raised.