Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias

Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, measure score deltas, and propose prompt-level mitigations. We argue that the same biases admit a representation-level account in the judge's hidden state, complementary to the input-output view and operationally useful in ways it does not afford. We report three findings, across seven judges, seven bias types, and nine benchmarks. Geometry: baseline judging inputs occupy a tight activation manifold while biased inputs are displaced along a low-dimensional, type-specific subspace that sharpens with depth and is recovered consistently by three families of estimators. Causal control: steering hidden states along this subspace drives scoring in both directions, forward shifts reproducing biased scoring on clean inputs and reverse shifts restoring baseline scoring on biased ones, while matched-norm random directions produce shifts an order of magnitude smaller. Operational: a simple linear projection onto the same bias-direction features anticipates judge failures on three entirely unseen benchmarks, substantially outperforming text-based alternatives. Reading bias as activation geometry, rather than as input-output noise, unifies geometric structure, causal control, and operational prediction within a single framework. The project page is available at https://xzx34.github.io/unfair-judge/

Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains

Tool-augmented multimodal agents show strong benchmark gains, often taken as evidence that agents have learned to use tools. We argue that this interpretation can be premature: a tool-call trace alone does not show whether the tool supplied answer-critical information. We study two representative ``thinking with images'' agents, Thyme and DeepEyesV2, across real-world understanding, OCR, chart understanding, and mathematical reasoning. Each agent is compared with its Tool-Free counterpart and with a Pure-Text Reasoner trained from the same source pool without tool-calling trajectories. Tool access yields little consistent aggregate improvement, does not reliably reduce generated-token cost, and leaves only a small tool-only solved set: 93% of DeepEyesV2's tool-solved problems and 96% of Thyme's are also solved by at least one non-tool setting. Mechanism ablations further show that the full tool-use loop does not consistently outperform either the tool-call format or the returned execution result alone. In the settings we study, the analyzed agents appear to learn tool-calling patterns more reliably than tool-contributed capabilities, suggesting that evaluation should distinguish tool availability from whether tools actually expand what agents can solve.

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning

Recent latent visual reasoning methods achieve substantial gains by inserting continuous latent tokens into multimodal language models. These gains are commonly attributed to the tokens encoding visual evidence; recent analyses, however, reveal a paradox: the tokens are loosely tied to the image and contribute little to the answer. Critically, these analyses treat latent tokens as a single unit, obscuring the true source of the gains. We therefore decompose latent tokens into three testable components: latent slots, boundary markers, and format, and develop a state-of-the-art method as a probe under favorable conditions. Across six method-stage settings and four perception-heavy benchmarks, latent slots fail every prediction of the visual-memory account. Strikingly, retaining only the boundary markers preserves 78 to 100% of the gain in several settings, while the model attends to the image more narrowly at latent positions than at answer positions. The gain therefore comes from boundary markers, format, and this attention pattern, not from latent slots. How each method engages this mechanism depends on its training supervision: at matched accuracy, mechanisms can still differ markedly. Latent visual reasoning thus needs evaluation not only by accuracy but by what the model actually relies on.

Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancing complex reasoning in large language models, and recent work extends RLVR to multimodal large language models (MLLMs). This transfer, however, surfaces a faithfulness challenge: faithful perception of task-relevant visual evidence and faithful use of that evidence during reasoning, leading to unsatisfactory gains on multimodal benchmarks. Specifically, existing perception supervision often operates on textual descriptions rather than natively on image regions, and faithful use is largely overlooked, exposing the perception-reasoning disconnect where correctly perceived evidence is dropped or contradicted during reasoning. To close these gaps, we propose Faithful-MR1, a training framework that anchors and reinforces visual attention to address both halves of faithful multimodal reasoning. The Anchoring stage turns perception into an explicit pre-reasoning subtask, supervising a dedicated <Focus> token's attention directly against image regions rather than through textual descriptions. The Reinforcing stage exposes faithful use through counterfactual image intervention, rewarding answer-correct trajectories that concentrate visual attention where vision causally matters. Extensive experiments demonstrate that Faithful-MR1 outperforms recent multimodal reasoning baselines on both Qwen2.5-VL-Instruct 3B and 7B backbones while using substantially less training data.