NeurIPS 2026 论文列表

The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, such as financial reports. While page-level chunking and retrieval is a natural starting point, it creates a critical bottleneck: delivering entire pages to the generator introduces excessive extraneous context. This not only overloads the generator's attention mechanism but also dilutes the most salient evidence. Moreover, compressing these information-rich pages into a limited visual token budget further increases the risk of hallucinations. To address this, we introduce AgenticOCR, a dynamic parsing approach that extends optical character recognition (OCR) from a static, full-text process into a query-driven, on-demand extraction system. By autonomously analyzing document layout in a "thinking with images" manner, AgenticOCR identifies and selectively recognizes regions of interest. This approach performs on-demand decompression of visual tokens precisely where needed, effectively decoupling retrieval granularity from rigid page-level chunking. AgenticOCR has the potential to serve as the "third building block" of the visual document RAG stack, operating alongside and enhancing standard Embedding and Reranking modules. Experimental results demonstrate that AgenticOCR improves both the accuracy and efficiency of visual RAG systems with pixel-adaptive per-image token allocation (e.g., Qwen3.5 generator), achieving expert-level performance in long document understanding. Our repository is anonymously available at https://anonymous.4open.science/r/AgenticOCR.

Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge---a capacity known in cognitive science as metamemory. We bring this perspective to LLMs by treating memory management as a trainable skill. We promote file-system operations to first-class memory actions alongside task actions, letting the model itself decide how to manage its memory. This memory skill improves along two axes: the structure that supports it (prompts, file schemas, action vocabulary), and the proficiency of the model exercising it. Both axes resist manual optimization: episodes in long-horizon tasks run for thousands of steps, and a single memory mistake can hide long before it surfaces, making human review of full trajectories impractical. We introduce AUTOMEM, a framework that automates both axes. In the first loop, a strong LLM reviews complete agent trajectories and iteratively revises the memory structure that shapes how the agent interacts with its memory files. In the second loop, the agent's own good memory decisions are identified from many episodes and used as training signal to sharpen the model's memory proficiency directly. Across three procedurally generated long-horizon games (Crafter, MiniHack, and NetHack), optimizing memory alone---without modifying the model's task-action behavior---improved the base agent's performance 2x--4x, bringing a 32B open-weight model competitive with frontier systems such as Claude Opus 4.5 and Gemini 3.1 Pro. Our results show that memory management is an independently learnable skill, and a high-leverage objective yielding large gains on long-horizon tasks.

Document QA agents do not fail only at the final answer. They can also write unsupported claims into public working memory, and those writes can affect later retrieval and synthesis. We introduce ADMIT (Auditable Decoupled Memory-write admission for Intermediate Traces), a low-budget admission controller for public OCR/text evidence packs. ADMIT applies a deterministic substring-support check $S_{\text{str}}(\hat{y}, B) > 0$ to each public commit and allows one bounded RepairRead. If repair still fails, ADMIT uses a memory-fail-closed / output-fail-open rule: it writes a $\bot$ (NO_COMMIT) sentinel to memory while the final-answer surface may still fall back to the baseline answer. On held-out M3DocVQA, a retrained final-row router closes the answer-surface gap; ADMIT's distinguishing evidence is therefore memory-surface contamination, not final-answer accuracy. The lexical invariant guarantees zero-substring accepted intermediate contamination by construction; the contribution is therefore the public memory-write boundary as a low-cost control surface with decoupled fail actions, not the invariant itself. In a 7-arm dynamic stress diagnostic on three agents, ADMIT enforces the invariant and preserves raw EM at this operating point (zero contaminated trajectories on every agent and no detectable raw-EM loss relative to the fail-open ablation), whereas final-only baselines still leave $12$--$32%$ contamination. ADMIT enforces lexical auditability, not semantic truth: relation-level entailment, citation-aware faithfulness, and visual-region grounding are not claimed, and lower-density VisDoMSlide and text-only FRAMES are reported as boundary cases.