💡 The paper introduces WebWatcher, a multimodal agent designed to improve visual-language reasoning in deep research tasks. The problem addressed is that most existing research agents are text-centric and overlook visual information, making multimodal deep research challenging. To solve this, WebWatcher is equipped with enhanced visual-language reasoning capabilities, leveraging synthetic multimodal trajectories for efficient training, utilizing various tools for deep reasoning, and enhancing generalization through reinforcement learning.

The method involves using high-quality synthetic multimodal trajectories for cold start training, which allows the agent to learn from both visual and textual information. The agent is also designed to work with various tools to improve its reasoning abilities. Additionally, the paper proposes a new benchmark called BrowseComp-VL, which is used to evaluate the capabilities of multimodal agents in complex information retrieval tasks involving both visual and textual information.

The results show that WebWatcher significantly outperforms existing baseline agents, including proprietary and open-source agents, in four challenging visual question answering benchmarks. This demonstrates the effectiveness of WebWatcher in solving complex multimodal information-seeking tasks and paves the way for further research in this area. Overall, the paper contributes to the development of multimodal agents with stronger reasoning abilities, which can handle both visual and textual information, and provides a new benchmark for evaluating the performance of such agents.

💡 The paper LongTraceRL addresses the challenge of long-context reasoning in large language models. Long-context reasoning is a central challenge for these models as they often fail to locate and integrate key information in extensive distracting content. Existing methods using reinforcement learning with verifiable rewards have shown promise but are limited by low-confusability distractors and sparse reward signals that cannot supervise intermediate reasoning steps.

To address these issues, the authors introduce LongTraceRL, a method that uses tiered distractor construction and rubric reward design to improve reasoning quality. For data construction, the authors generate multi-hop questions via knowledge graph random walks and leverage search agent trajectories to build tiered distractors. These distractors include documents the agent read but did not cite, which are high in confusability, and documents that appeared in search results but were never opened, which are low in confusability. This approach produces training contexts that are far more challenging than those built by random sampling or one-shot search.

The authors also propose a rubric reward that uses gold entities along each reasoning chain as fine-grained, entity-level process supervision. This reward is applied only to responses with correct final answers, which distinguishes the reasoning quality among correct responses and prevents reward hacking.

The experiments on three reasoning large language models across five long-context benchmarks demonstrate that LongTraceRL consistently outperforms strong baselines and encourages comprehensive, evidence-grounded reasoning. The results show that LongTraceRL is effective in improving the long-context reasoning capabilities of large language models. The codes, datasets, and models are available for further research and development. Overall, LongTraceRL provides a new approach to addressing the challenge of long-context reasoning in large language models and has the potential to improve the performance of these models in a variety of applications.

💡 The paper introduces COLLEAGUE SKILL, a system for automatically generating person-grounded AI skills from heterogeneous traces of expert knowledge. The problem addressed is that current methods for creating AI agents that mimic human expertise and judgment are limited, as they rely on fragmented evidence and lack a comprehensive workflow for distilling this knowledge into usable skills.

The method presented involves an automated trace-to-skill distillation process that takes materials from a target person or role and produces a versioned skill package with two tracks: a capability track for practices, mental models, and decision heuristics, and a bounded behavior track for communication style, interaction rules, and correction history. This package can be inspected, updated through natural-language feedback, and deployed across agent hosts.

The results of the system are significant, with the open-source repository having approximately 18.5k GitHub stars, 215 skills from 165 contributors, and over 100k cumulative stars across listed skill cards. The system demonstrates how person-grounded skills can be represented as portable, correctable packages, rather than opaque prompts or hidden memories, and provides a comprehensive workflow for generating and deploying these skills. The paper presents the artifact contract, generation workflow, correction lifecycle, deployment surface, and domain presets implemented in the system, showcasing its potential for creating more human-like AI agents.

💡 The paper discusses a new type of attack called multi-step trojan attacks that can bypass existing defenses in local language model agents. These agents can read and write files, call tools, and reuse workspace state across sessions, making them useful but also vulnerable to attacks. Attackers can embed malicious prompts within files or tool outputs, which the agent can then execute later, allowing them to gain persistent control over the system. The problem with existing defenses is that they inspect each step in isolation, so they can block a clear harmful action but fail to detect the earlier operation that planted the backdoor.

To address this threat, the authors introduce ClawTrojan, a benchmark designed to identify multi-step trojan attacks in local agentic harnesses. They tested ClawTrojan in a simulated workspace with a language model and found that it achieved a 95.5 percent attack success rate, while existing single-turn prompt-injection attacks had near-zero success rates on the same model.

To defend against these attacks, the authors propose DASGuard, a system that scans control-like text in sensitive local files, traces its origin, and removes control content that does not originate from a trusted source. The results show that DASGuard achieves strong dynamic defense by combining runtime attack blocking with sanitized commits to the workspace. Overall, the paper contributes to the development of new detection methods and defense strategies against multi-step trojan attacks in local language model agents.

💡 The paper presents AutoFigure-Edit, a system that generates editable scientific illustrations from text descriptions and reference images. The problem addressed is that existing automated systems for creating scientific illustrations are limited in their ability to be edited, styled, and refined efficiently. To solve this, AutoFigure-Edit combines long-context understanding, reference-guided styling, and native SVG editing to enable the creation of high-quality scientific illustrations that can be easily edited and refined. The system allows for flexible style adaptation through user-provided reference images, making it possible to generate illustrations in various styles. The results of the paper include the development of the AutoFigure-Edit system, which is made available through a website, a video demonstration, and an open-source codebase, facilitating further progress in the field of automated scientific illustration generation. The system enables efficient creation and refinement of high-quality scientific illustrations, making it a valuable tool for communicating complex scientific and technical concepts.

💡 The paper LongLive-RAG addresses the challenge of generating long videos using autoregressive video diffusion models. The problem with existing methods is that they use sliding-window attention, which can lead to error accumulation and identity drift over time. This is because once the active window accumulates appearance errors, subsequent generations can only condition on this degraded trajectory and drift further away. To overcome this limitation, the authors propose a retrieval-augmented generation framework called LongLive-RAG.

In this framework, previously generated latents are treated as a dynamic and searchable history. At each new block, LongLive-RAG uses a query embedding to retrieve relevant historical latents, allowing the generator to condition on non-local context instead of only the recent window. This retrieval step adds only a small overhead relative to generation and helps reduce error accumulation.

To make retrieval more discriminative, the authors introduce the Window Temporal Delta Loss, which suppresses redundant local similarity and encourages embeddings to capture meaningful temporal changes. The LongLive-RAG framework is general and can be used with multiple autoregressive backbones and generation lengths.

The experiments show that LongLive-RAG improves long video quality and achieves the best average VBench-Long rank. The authors claim that LongLive-RAG is the first method to formulate self-generated latent history as content-addressable retrieval memory, making it a significant contribution to the field of long video generation. The code for LongLive-RAG is available, making it possible for others to build upon and extend this work. Overall, the paper presents a novel approach to long video generation that addresses the limitations of existing methods and achieves state-of-the-art results.

💡 The paper addresses the challenge of creating high-quality scientific illustrations, which is a time-consuming and labor-intensive process. To tackle this problem, the authors introduce FigureBench, a large-scale benchmark consisting of 3300 high-quality scientific text-figure pairs, covering various text-to-illustration tasks from different sources. This benchmark provides a foundation for training and evaluating models that generate scientific illustrations from long-form scientific texts.

The authors also propose AutoFigure, an agentic framework that automatically generates high-quality scientific illustrations based on long-form scientific texts. AutoFigure engages in extensive thinking, recombination, and validation processes to produce a layout that is both structurally sound and aesthetically refined, resulting in a scientific illustration that achieves both structural completeness and aesthetic appeal.

The performance of AutoFigure is evaluated using the FigureBench benchmark, and the results demonstrate that AutoFigure consistently outperforms various baseline methods, producing publication-ready scientific illustrations. The authors release the code, dataset, and other resources to facilitate further research and development in this area.

Overall, the paper contributes to the development of automated tools for generating high-quality scientific illustrations, which can help alleviate the bottleneck in creating these illustrations and improve the communication of complex scientific and technical concepts. The introduction of FigureBench and AutoFigure provides a significant step forward in this direction, with the potential to benefit both academia and industry.