让智能终端代理学会分辨有用和无用指令，避免被误导。
No More, No Less: Task Alignment in Terminal Agents
- 设计89个需从环境文件中筛选关键信息的任务
- 顶尖代理完成任务率高但忽略正确指令的比例达42%
- 适合研究智能体对指令的精准理解与安全防御
终端智能体正日益能从单一用户指令自主完成复杂、长周期任务。为此，它们必须解析环境中出现的指示（如README文件、代码注释、堆栈跟踪），并判断其与任务的相关性。这带来根本挑战：相关线索必须遵循，无关或误导性线索则需忽略。现有基准无法衡量此能力——代理可能因盲目执行所有指令而看似高效，也可能因完全忽略指令而显得鲁棒。我们提出TAB（任务对齐基准），包含89个源自Terminal-Bench 2.1的任务。每个任务故意信息不全，关键线索以自然环境产物形式嵌入（如配置文件），同时存在一个看似合理但无关的干扰项。解决任务需在两者间精准选择。对十款前沿代理的测试显示，任务完成能力与任务对齐间存在系统性差距：最强的Terminal-Bench代理任务完成率高达87%，但在TAB上任务对齐率仅为42%。进一步评估六种提示注入防御机制发现，抑制干扰执行也同时削弱了任务完成所需的关键线索利用。结果表明，真正对齐的代理需具备对环境指令的精准选择能力，而非全盘接受或拒绝。
原文摘要 · Abstract (English)
Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret instructions encountered in the environment (e.g., README files, code comments, stack traces) and determine their relevance to the task. This creates a fundamental challenge: relevant cues must be followed to complete a task, whereas irrelevant or misleading ones must be ignored. Existing benchmarks do not capture this ability. An agent may appear capable by blindly following all instructions, or appear robust by ignoring them altogether. We introduce TAB (Task Alignment Benchmark), a suite of 89 terminal tasks derived from Terminal-Bench 2.1. Each task is intentionally underspecified, with missing information provided as a necessary cue embedded in a natural environmental artifact, alongside a plausible but irrelevant distractor. Solving these tasks requires selectively using the cue while ignoring the distractor. Applying TAB to ten frontier agents reveals a systematic gap between task capability and task alignment. The strongest Terminal-Bench agent achieves high task completion but low task alignment on TAB. Evaluating six prompt-injection defenses further shows that suppressing distractor execution also suppresses the cues required for task completion. These results demonstrate that task-aligned agents require selective use of environmental instructions rather than blanket acceptance or rejection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。