Jize Jiang

Ke Yang, Zixi Chen, Xuan He et al.

Long-term memory is essential for large language model (LLM) agents operating in complex environments, yet existing memory designs are either task-specific and non-transferable, or task-agnostic but less effective due to low task-relevance and context explosion from raw memory retrieval. We propose PlugMem, a task-agnostic plugin memory module that can be attached to arbitrary LLM agents without task-specific redesign. Motivated by the fact that decision-relevant information is concentrated as abstract knowledge rather than raw experience, we draw on cognitive science to structure episodic memories into a compact, extensible knowledge-centric memory graph that explicitly represents propositional and prescriptive knowledge. This representation enables efficient memory retrieval and reasoning over task-relevant knowledge, rather than verbose raw trajectories, and departs from other graph-based methods like GraphRAG by treating knowledge as the unit of memory access and organization instead of entities or text chunks. We evaluate PlugMem unchanged across three heterogeneous benchmarks (long-horizon conversational question answering, multi-hop knowledge retrieval, and web agent tasks). The results show that PlugMem consistently outperforms task-agnostic baselines and exceeds task-specific memory designs, while also achieving the highest information density under a unified information-theoretic analysis. Code and data are available at https://github.com/TIMAN-group/PlugMem.

Adam Davies, Jize Jiang, ChengXiang Zhai

Despite the recent successes of large, pretrained neural language models (LLMs), comparatively little is known about the representations of linguistic structure they learn during pretraining, which can lead to unexpected behaviors in response to prompt variation or distribution shift. To better understand these models and behaviors, we introduce a general model analysis framework to study LLMs with respect to their representation and use of human-interpretable linguistic properties. Our framework, CALM (Competence-based Analysis of Language Models), is designed to investigate LLM competence in the context of specific tasks by intervening on models' internal representations of different linguistic properties using causal probing, and measuring models' alignment under these interventions with a given ground-truth causal model of the task. We also develop a new approach for performing causal probing interventions using gradient-based adversarial attacks, which can target a broader range of properties and representations than prior techniques. Finally, we carry out a case study of CALM using these interventions to analyze and compare LLM competence across a variety of lexical inference tasks, showing that CALM can be used to explain behaviors across these tasks.

Banghao Chi, Yining Xie, Mingyuan Wu et al.

Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks, such as controlling computers and generating presentations, building an AI-driven spreadsheet agent has emerged as a promising research direction. Most existing spreadsheet agents rely on specialized prompting over general-purpose LLMs; while this design has potentials on simple spreadsheet operations, it struggles to manage the complex, multi-step workflows typical of real-world applications. We introduce Spreadsheet-RL, a reinforcement learning (RL) fine-tuning framework designed to train specialized spreadsheet agents within a realistic Microsoft Excel environment. Spreadsheet-RL features an automated pipeline for scalable collection of paired start-goal spreadsheets from online forums, as well as domain-specific evaluation tasks in areas such as finance and supply chain management, which we compile into the new Domain-Spreadsheet benchmark dataset. It also includes a Spreadsheet Gym environment designed for multi-turn RL: Spreadsheet Gym exposes extensive Excel functionality through a Python sandbox, along with a refined harness that incorporates a comprehensive tool set and carefully designed tool-routing rules for spreadsheet tasks. Through comprehensive experiments, we show that Spreadsheet-RL substantially enhances AI agent's performance on both general and domain-specific spreadsheet tasks: it improves Qwen3-4B-Thinking-2507's Pass@1 on SpreadsheetBench from 12.0% to 23.4%, and raises Pass@1 from 8.4% to 17.2% on our curated Domain-Spreadsheet dataset. These results highlight Spreadsheet-RL's strong potential for generalization and real-world adoption in spreadsheet automation, and broadly, its promise for advancing LLM-based interactions with data interfaces in everyday work.

Xinyu Pi, Mingyuan Wu, Jize Jiang et al.

Smaller-scale Vision-Langauge Models (VLMs) often claim to perform on par with larger models in general-domain visual grounding and question-answering benchmarks while offering advantages in computational efficiency and storage. However, their ability to handle rare objects, which fall into the long tail of data distributions, is less understood. To rigorously evaluate this aspect, we introduce the "Uncontextualized Uncommon Objects" (UOUO) benchmark. This benchmark focuses on systematically testing VLMs with both large and small parameter counts on rare and specialized objects. Our comprehensive analysis reveals that while smaller VLMs maintain competitive performance on common datasets, they significantly underperform on tasks involving uncommon objects. We also propose an advanced, scalable pipeline for data collection and cleaning, ensuring the UOUO benchmark provides high-quality, challenging instances. These findings highlight the need to consider long-tail distributions when assessing the true capabilities of VLMs.

Mingyuan Wu, Jize Jiang, Haozhen Zheng et al.

Vision Language Models (VLMs) have achieved remarkable success in a wide range of vision applications of increasing complexity and scales, yet choosing the right VLM model size involves a trade-off between response quality and cost. While smaller VLMs are cheaper to run, they typically produce responses only marginally better than random guessing on benchmarks such as MMMU. In this paper, we propose Cache of Thought (CoT), a master apprentice framework for collaborative inference between large and small VLMs. CoT manages high quality query results from large VLMs (master) in a cache, which are then selected via a novel multi modal retrieval and in-context learning to aid the performance of small VLMs (apprentice). We extensively evaluate CoT on various widely recognized and challenging general reasoning benchmarks, and show that CoT increases overall reasoning performance by up to 7.7% under the same budget, and specifically boosts the performance of apprentice VLMs by up to 36.6%. Our code is available at https://github.com/UIUC-MONET/Cache-of-Thoughts

Mingyuan Wu, Jingcheng Yang, Jize Jiang et al.

Reinforcement Learning Finetuning (RFT) has significantly advanced the reasoning capabilities of large language models (LLMs) by enabling long chains of thought, self-correction, and effective tool use. While recent works attempt to extend RFT to vision-language models (VLMs), these efforts largely produce text-only reasoning conditioned on static image inputs, falling short of true multimodal reasoning in the response. In contrast, test-time methods like Visual Sketchpad incorporate visual steps but lack training mechanisms. We introduce VTool-R1, the first framework that trains VLMs to generate multimodal chains of thought by interleaving text and intermediate visual reasoning steps. VTool-R1 integrates Python-based visual editing tools into the RFT process, enabling VLMs to learn when and how to generate visual reasoning steps that benefit final reasoning. Trained with outcome-based rewards tied to task accuracy, our approach elicits strategic visual tool use for reasoning without relying on process-based supervision. Experiments on structured visual question answering over charts and tables show that VTool-R1 enhances reasoning performance by teaching VLMs to "think with images" and generate multimodal chain of thoughts with tools.

Mingyuan Wu, Meitang Li, Jingcheng Yang et al.

Inference-time techniques such as decoding-time scaling and self-refinement have been shown to substantially improve reasoning in large language models (LLMs), driven by emergent self-correction and self-verification behaviors often elicited through reinforcement learning (RL). In this work, we investigate whether these inference-time scaling methods similarly benefit vision-language models (VLMs), especially those fine-tuned with RL. Through extensive evaluation, we find that while strategies like majority vote and best-of-N with self-verification enhance VLM performance, majority vote significantly outperforms verification-centric ones. Furthermore, inference time scaling behaviors commonly associated with RL-tuned models, such as the 'A-ha moment,' do not yield consistent performance gains. Our analysis identifies a key limitation: current RL-trained VLMs exhibit weak self-verification across both visual and textual modalities, limiting the effectiveness of inference-time scaling.

Ziyi Chen, Jize Jiang, Daqian Zuo et al.

In recent RAG approaches, rerankers play a pivotal role in refining retrieval accuracy with the ability of revealing logical relations for each pair of query and text. However, existing rerankers are required to repeatedly encode the query and a large number of long retrieved text. This results in high computational costs and limits the number of retrieved text, hindering accuracy. As a remedy of the problem, we introduce the Efficient Title Reranker via Broadcasting Query Encoder, a novel technique for title reranking that achieves a 20x-40x speedup over the vanilla passage reranker. Furthermore, we introduce Sigmoid Trick, a novel loss function customized for title reranking. Combining both techniques, we empirically validated their effectiveness, achieving state-of-the-art results on all four datasets we experimented with from the KILT knowledge benchmark.