The Agent Capability Problem: Predicting Solvability Through Information-theoretic Bounds

Abstract

When should an autonomous agent commit resources to a task? We introduce the Agent Capability Problem (ACP), a framework for predicting whether an agent can solve a problem under resource constraints. Rather than relying on empirical heuristics, ACP frames problem-solving as information acquisition: an agent requires \(\Itotal\) bits to identify a solution and gains \(\Istep\) bits per action at cost \(\Cstep\), yielding an effective cost \(\Ceff = (\Itotal/\Istep), \Cstep\) that predicts resource requirements before search. We prove that \(\Ceff\) lower-bounds expected cost and provide tight probabilistic upper bounds. Experimental validation shows that ACP predictions closely track actual agent performance, consistently bounding search effort while improving efficiency over greedy and random strategies. The framework generalizes across LLM-based and agentic workflows, linking principles from active learning, Bayesian optimization, and reinforcement learning through a unified informat

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylutati2025the

Related papers

• A Mathematical Theory Of Agency And Intelligence (2026)0.00
• Hil-bench (human-in-loop Benchmark): Do Agents Know When To Ask For Help? (2026)0.00
• CAPO: Counterfactual Credit Assignment In Sequential Cooperative Teams (2026)0.00
• CARL: Focusing Agentic Reinforcement Learning On Critical Actions (2025)0.00
• Autonomous Capability Assessment Of Sequential Decision-making Systems In Stochastic Settings (extended Version) (2023)0.00
• Information-theoretic Methods For Planning And Learning In Partially Observable Markov Decision Processes (2016)0.00
• On The Statistical Limits Of Self-improving Agents (2025)0.00
• Reasoning About Unforeseen Possibilities During Policy Learning (2018)0.00