# From Sycophancy to Sensemaking: Premise Governance for Human-AI Decision Making

arXiv: https://arxiv.org/abs/2602.02378 · HTML: https://mlsanity.com/paper/2602.02378/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025)
- [Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2](https://mlsanity.com/paper/2502.03544/) (2025)
- [Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?](https://mlsanity.com/paper/2511.13646/) (2025)
- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery](https://mlsanity.com/paper/2504.01205/) (2025)
- [Interaction, Process, Infrastructure: A Unified Framework for Human-Agent Collaboration](https://mlsanity.com/paper/2506.11718/) (2025)
- [VIGIL: A Reflective Runtime for Self-Healing Agents](https://mlsanity.com/paper/2512.07094/) (2025)
- [Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support](https://mlsanity.com/paper/2512.07801/) (2025)

## Abstract (arXiv)

As LLMs expand from assistance to decision support, a dangerous pattern emerges: fluent agreement without calibrated judgment. Low-friction assistants can become sycophantic, baking in implicit assumptions and pushing verification costs onto experts, while outcomes arrive too late to serve as reward signals. In deep-uncertainty decisions (where objectives are contested and reversals are costly), scaling fluent agreement amplifies poor commitments faster than it builds expertise. We argue reliable human-AI partnership requires a shift from answer generation to collaborative premise governance over a knowledge substrate, negotiating only what is decision-critical. A discrepancy-driven control loop operates over this substrate: detecting conflicts, localizing misalignment via typed discrepancies (teleological, epistemic, procedural), and triggering bounded negotiation through decision slices. Commitment gating blocks action on uncommitted load-bearing premises unless overridden under logged risk; value-gated challenge allocates probing under interaction cost. Trust then attaches to auditable premises and evidence standards, not conversational fluency. We illustrate with tutoring and propose falsifiable evaluation criteria.