# ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps

arXiv: https://arxiv.org/abs/2610.20532 · HTML: https://mlsanity.com/paper/2610.20532/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [Distribution-Free, Risk-Controlling Prediction Sets](https://mlsanity.com/paper/2101.02703/) (2021)
- [Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control](https://mlsanity.com/paper/2110.01052/) (2021)
- [Defining and Characterizing Reward Hacking](https://mlsanity.com/paper/2209.13085/) (2022)
- [AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition](https://mlsanity.com/paper/2512.03794/) (2025)
- [DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning](https://mlsanity.com/paper/2512.07132/) (2025)
- [ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use](https://mlsanity.com/paper/2510.27363/) (2025)
- [An Approximate Nonmyopic Computation for Value of Information](https://mlsanity.com/paper/1303.5720/) (2013)
- [Value of Information Lattice: Exploiting Probabilistic Independence for Effective Feature Subset Acquisition](https://mlsanity.com/paper/1401.3881/) (2014)

## Abstract (arXiv)

A multimodal agent must decide whether visual evidence is worth acquiring, which candidate or resolution to query, and when further interaction can no longer change its decision. We study this problem under a strict free-metadata/paid-observation boundary, stochastic vector costs, and a frozen execution trace, and treat it as decision-certifiable active evidence acquisition. A Counterfactual Evidence Interaction Graph (CEIG) represents unary evidence value, signed second-order interaction, and directed conditional harm while maintaining explicit score enclosures for unresolved interactions; a decision-weighted enclosure objective tightens the bounds that can change action identity. Gap-directed refinement evaluates only interactions that can displace the incumbent acquisition and stops once an ε-decision certificate shows that unresolved terms cannot change the selected action beyond a declared tolerance. The certificate is model-relative: it verifies policy-consistent optimality under the pinned learned score, and semantic quality is measured separately through post-freeze labels. Paired continuation rollouts learn the downstream value of paid previews, an online operational cost filter is separated from independent finite-policy-family trajectory certification, and an acquisition monitor with an independently implemented verifier binds every certificate to the frozen trace. On 640 cases split into 384/128/128 training, validation, and test cases, the controller reaches task score 0.842, grounding F1 0.816, evidence recall 0.873, 1.74 accepted calls, 286.5K visual tokens, and 742ms p95 latency. Dense replay of issued certificates shows 0.992 action agreement and a 0.988 certificate rate while evaluating 19.6 instead of 191.4 expensive interaction terms per decision.