Prediction and Empowerment: A Theory of Agency through Bridge Interfaces

• URL: http://arxiv.org/abs/2605.06346v1
• Date: Thu, 07 May 2026 14:30:46 GMT
• Title: Prediction and Empowerment: A Theory of Agency through Bridge Interfaces
• Abstract summary: We study agency under partial observability in deterministic physical or simulated worlds.<n>We prove a separation between prediction, compression, and empowerment.<n>For modern AI agents, the results suggest a design principle rather than a theorem of inevitability.
• Score: 0.10152838128195464
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study agency under partial observability in deterministic physical or simulated worlds, where apparent randomness arises from uncertainty over initial conditions, fixed law bits, and unrolled exogenous noise. We model sensing and actuation as bridge interfaces split between agent-controlled parameters and environment-controlled channel state, inducing a deterministic POMDP through a prior over latent microstates and many-to-one observation coarsening. Within this framework, we prove a separation between prediction, compression, and empowerment. Perfect prediction can be achieved either by identifying the hidden quotient relevant to the target family or by overwrite control that makes the future target action-determined; high empowerment alone is insufficient. Under refinable interfaces and sufficient memory, action-conditioned observation-compression progress reduces posterior uncertainty about the latent quotient, and when refinement requires steering world-side channel conditions, this creates target-conditioned interface empowerment. A bit-string specialization with a conserved information budget makes the resulting tradeoff explicit: prediction by identification requires internal capacity at least the relevant latent entropy, whereas overwrite control requires terminal action capacity over the controlled quotient. For modern AI agents, the results suggest a design principle rather than a theorem of inevitability: objectives should distinguish hidden-state identification, interface refinement, task-relevant controllability, and mere overwrite or distractor control. Human--AI alignment is partly an interface-design problem, where the relevant bridge is between human intent, agent internal state, external tools, and world-side channel conditions. This is a working draft: feedback and criticism is most welcome.

Related papers

• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems [0.0]
  This paper explores the architectural vulnerability of unbounded autonomy.<n>We instantiate this theory via the SMARt model, a four-layer framework featuring Stable, Meta-cognitive, Assisted, and Regulated states.<n>We conclude that formalizing failure management within the autonomy lifecycle is a crucial step toward realizing reliable and governed artificial intelligence.
  arXiv  Detail & Related papers  (2026-05-26T19:49:23Z)
• Active Inference: A method for Phenotyping Agency in AI systems? [0.11904398364437437]
  We argue for a minimal notion open to principled inspection given three criteria.<n> posterior beliefs, prior preferences, and the minimization of expected free energy jointly constitute an agentic action chain.
  arXiv  Detail & Related papers  (2026-04-25T12:41:53Z)
• Beyond Fluency: Toward Reliable Trajectories in Agentic IR [0.0]
  This position paper synthesizes failure modes observed in industrial agentic systems.<n>We argue that safe deployment requires moving beyond endpoint accuracy toward trajectory integrity and causal attribution.
  arXiv  Detail & Related papers  (2026-04-05T21:20:57Z)
• What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty [1.6868147729303773]
  We prove "selection theorems" showing that low "average-case regret" forces an agent to implement a predictive, structured internal state.<n>We show that regret bounds limit probability mass on suboptimal bets, enforcing the predictive distinctions needed to separate high-margin outcomes.
  arXiv  Detail & Related papers  (2026-03-03T00:47:58Z)
• Pro-HOI: Perceptive Root-guided Humanoid-Object Interaction [57.252599851031505]
  We introduce Perceptive Root-guided Humanoid-Object Interaction, Pro-HOI.<n>Pro-HOI is a generalizable framework for robust humanoid loco-manipulation.<n> Empirical validation on a Unitree G1 robot demonstrates that Pro-HOI significantly outperforms baselines in generalization and robustness.
  arXiv  Detail & Related papers  (2026-03-01T14:19:59Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• The Lock-In Phase Hypothesis: Identity Consolidation as a Precursor to AGI [0.0]
  Large language models (LLMs) remain broadly open and highly steerable.<n>By analogy to human development, we hypothesize that progress toward artificial general intelligence (AGI) involves a lock-in phase.<n>We formalize this phase, link it to known phenomena in learning dynamics, and propose operational metrics for onset detection.<n>Our results reveal a spectrum of outcomes--from performance trade-offs in small models, through largely cost-free adoption in mid-scale models, to transient instabilities in large, quantized models.
  arXiv  Detail & Related papers  (2025-10-23T04:20:10Z)
• Cooperative Probabilistic Trajectory Forecasting under Occlusion [110.4960878651584]
  Occlusion-aware planning often requires communicating the information of the occluded object to the ego agent for safe navigation. In this paper, we design an end-to-end network that cooperatively estimates the current states of occluded pedestrian in the reference frame of ego agent. We show that the uncertainty-aware trajectory prediction of occluded pedestrian by the ego agent is almost similar to the ground truth trajectory assuming no occlusion.
  arXiv  Detail & Related papers  (2023-12-06T05:36:52Z)
• Reinforcement Learning with a Terminator [80.34572413850186]
  We learn the parameters of the TerMDP and leverage the structure of the estimation problem to provide state-wise confidence bounds. We use these to construct a provably-efficient algorithm, which accounts for termination, and bound its regret.
  arXiv  Detail & Related papers  (2022-05-30T18:40:28Z)
• An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction [84.49035467829819]
  We show that it is possible to better manage this trade-off by optimizing a bound on the Information Bottleneck (IB) objective. Our fully unsupervised approach jointly learns an explainer that predicts sparse binary masks over sentences, and an end-task predictor that considers only the extracted rationale.
  arXiv  Detail & Related papers  (2020-05-01T23:26:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.