工具使用何时会增强有限精度循环模型的表达能力?
When Does Tool Use Increase the Expressive Power of Finite-Precision Recurrent Models?
AI总结:
研究工具使用对有限精度循环模型表达能力的影响,通过将模型建模为与预言机交互的有限状态控制器,得出有限状态工具基本不增加表达能力,单个无限状态磁带使系统图灵完备,且特定单层控制器可实现此构造的结论。
摘要:
现代序列模型越来越多地被用作代理,将令牌生成与对外部工具的调用交织在一起。我们给出了这种工具访问何时会增加计算表达能力的精确架构层面的说明。我们将任何固定的有限精度循环序列模型,包括具有B位内部状态的有限精度状态空间模型(SSM),建模为通过有限命令/观察接口与预言机交互的确定性有限状态控制器。我们的结果形成了鲜明的二分法。首先,本身为有限状态的工具基本不会增加表达能力:乘积状态模拟以仅\(\log_2|M| + O(1)\)额外比特的代价将任何具有有限内存集M的有限状态有界接口预言机内化,因此增强后的系统仍是有限状态。其次,单个最小无限状态工具,即仅支持局部读取、写入和移动命令的磁带,使系统成为图灵完备:对于每个具有状态集Q和磁带字母表\(\Gamma\)的单磁带图灵机,具有\(O(\log|Q| + \log|\Gamma|)\)比特内部内存的控制器可以模拟它,并且我们展示了具体的指数分离:\(\mathrm{EQ}_n\)在没有工具时需要\(2^n\)个状态,但使用磁带工具时只需单个恒定大小的控制器。第三,我们表明这种构造恰好由具有二进制独热隐藏状态、\(\{0,1\}\)转移矩阵和零偏差的自然单层有限精度选择性仿射SSM控制器实现。选择性对该构造至关重要。在补充材料中,我们明确了所有常数,证明了对数预言机辅助通用模拟,其中\(O(\log B)\)个循环比特足以模拟任何B状态图灵机,并证明了匹配的不可能结果。
英文摘要:
Modern sequence models are increasingly deployed as agents that interleave token generation with calls to external tools. We study when such tool access increases computational expressivity. We model any fixed finite-precision recurrent sequence model, including finite-precision state-space models (SSMs) with $B$ bits of internal state, as a deterministic finite-state controller interacting with an oracle through a finite command/observation interface, and establish a separation between the two regimes analyzed. First, every finite-state bounded-interface tool with memory set $M$ can be internalized at a cost of at most $\lceil\log_2|M|\rceil+O(1)$ recurrent bits, so the combined system remains finite-state. Second, a single unbounded tape with only local $\mathtt{read}$/$\mathtt{write}$/$\mathtt{move}$ commands suffices for Turing completeness: every single-tape Turing machine with state set $Q$ and tape alphabet $Γ$ is simulated by a controller with $O(\log|Q|+\log|Γ|)$ recurrent bits, and $\mathrm{EQ}_n$ requires $2^n$ states without tools but one constant-size controller with the tape. Third, this construction is realized exactly by a one-layer finite-precision \emph{selective} affine SSM with binary one-hot states, $\{0,1\}$ transition matrices, and zero biases. Under explicitly stated resource conventions, $O(\log B)$ recurrent bits suffice for tape-assisted simulation of any $B$-state Turing machine, whereas directly realizing an arbitrary $B$-state transition map in one exact affine update without external memory requires total recurrent dimension exactly $B-1$. Fixed description size, occupied tape cells, and interaction cost are reported separately from recurrent memory. Our results concern exact expressivity under deterministic semantics, not learnability or empirical performance.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。