EVOKE Elicits Pretrained World Knowledge for Transferable Decision-Making via Fixed-State Goal Diversity

Background and the Problem

LLM agents struggle when transferring to unfamiliar environments. Conventional world-model approaches predict future visual/state observations, suffering from high training burdens and compounding roll-out errors. Because digital world knowledge is already internalized within base LLMs during pretraining, the core hurdle lies in post-training: single-goal supervision per state drives agents toward superficial contextual habits rather than causal reasoning.

Architecture and How It Works

EVOKE supplies targeted pressure to elicit latent world knowledge through goal diversity at fixed states:

1. Fixed-State Counterfactual Objectives: Holds the environmental state and conversation history invariant while introducing alternative goals.
2. Action Preference Re-ranking: Compels the agent to re-rank identical candidate actions under varying goals. Superficial context-matching fails under this regime, forcing the policy to simulate underlying state-action transitions.
3. Direct Decision Supervision: Bypasses explicit observation prediction networks, activating latent world representations directly through preference alignment objectives.

Benchmarks and Measured Results

Evaluated across multiple multi-step agent decision benchmarks across three model backbones:

1. 14.3% Boost on Unseen Environments: EVOKE lifts task success on completely unseen environments by 14.3 percentage points over standard single-goal post-training while reducing redundant exploratory steps by 26%.
2. Exceptional Sample Efficiency: Matches and exceeds standard full-dataset baselines using only 40% of the trajectory training data.
3. Shortcut Suppression: Probing experiments confirm enhanced state-goal decoupling in representation space, eliminating vulnerability to misleading prompt artifacts.

Getting Started for Developers

EVOKE is open-sourced on GitHub with modular loss implementations and data augmentation scripts. Practitioners building enterprise RPA agents or cross-platform assistants can integrate fixed-state counterfactual goal swapping into existing DPO pipelines to unlock robust out-of-distribution transfer without adding inference latency.