News without the noise
Digests of notable academic papers, primarily from arXiv
212 articles · page 5 of 5
Genewein et al. present a report examining how AI might develop beyond human-level AGI to artificial superintelligence (ASI). They characterize ASI as systems more cognitively capable than large organizations of humans, outline four possible pathways, and conclude that a single step-change event may be less likely than a series of transformative, AI-driven breakthroughs.
The authors introduce Claw-SWE-Bench, a benchmark and adapter protocol for evaluating OpenClaw-style agent harnesses (claws) on coding tasks. They show that adapter design dramatically affects performance: OpenClaw with a minimal adapter scores only 19.1% Pass@1, while a full adapter achieves 73.4% with the same backbone model. The benchmark also reveals that model choice and harness choice each account for roughly 30 percentage points of variation in performance.
The authors propose Decentralized Language Models (DeLM), a multi-agent framework that replaces a central controller with a shared context and task queue, allowing agents to asynchronously claim subtasks and build on verified progress. On SWE-bench Verified, DeLM improved performance by up to 10.5 percentage points and reduced costs by roughly 50%. On LongBench-v2, it achieved the highest average accuracy across four frontier model families.
The authors test four context engineering strategies for GPT-5 agents using Model Context Protocol tools on a 50-task hotel expense benchmark. They find that pruning context to the last five tool call/response pairs and adding automated summarization yields the best results: 91.6% complete itemization, 99.64% amount itemized, with 63% fewer tokens and 60% less runtime than retaining full conversation history.
The authors propose SceneConductor, a multi-agent framework that generates complete 3D scenes from a single input image. It decomposes the task into three stages—scene initialization, environment construction, and multi-agent refinement—and introduces a geometry-aware layout predictor trained with sparse point-map priors. The method outperforms prior approaches on geometric accuracy, spatial consistency, and perceptual realism across benchmark datasets.
The authors introduce Alem, a JAX-based benchmark for open-ended multi-agent coordination built on Craftax-like dynamics. Evaluating 13 modern LLMs zero-shot in homogeneous teams, they find that current agents average only ~6% normalized return, with individual task competence failing to predict coordination performance.
The authors present IEA, a conversational image editing agent that manipulates 16 parameterized tools step by step instead of generating pixels directly. Trained via a three-stage multitask pipeline, IEA achieves lower pixel distance on editing tasks and higher ROUGE-L on intent summaries than strong baselines, and outperforms both tool-calling and generative methods in user studies.
The authors propose Astra, an agentic spatial reasoning framework that combines two components: a world simulator (Astra-WM) that generates novel-view images from context images and natural-language camera motions, and an RL-trained VLM policy (Astra-VL) that decides when to query the simulator. Trained with view consistency tuning and a two-phase RL curriculum, Astra improves spatial reasoning benchmarks by 9–10 points over direct VLM answering, demonstrating that effective world-model-augmented reasoning requires learning when, where, and how to imagine.
The authors present the first systems-level characterization of LLM agent memory systems. They introduce a taxonomy, build a phase-aware profiler, and evaluate ten systems across two benchmarks, showing how design choices shift computational costs between memory construction and retrieval. Key recommendations include construction scheduling and amortization via query volume.
The authors propose MAGE, a memory system that treats an agent's history as an execution-state tree rather than a semantically organized document store. On the MemoryArena benchmark, MAGE raised average task success by 7.8–20.4 percentage points over RAG-based baselines while cutting token use by 55.1%.
The authors introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimizes an AI agent's harness of skills, tools, and workflows using only past task trajectories. By selecting a diverse coreset of challenging tasks, re-solving them in parallel, and using self-validation to pick the best harness update, the method improves pass rate on SWE-Bench Pro from 59% to 78% in a single optimization round.
The authors present PROVE, a framework for reinforcement learning (RL) on multi-step tool use that overcomes three key obstacles: lack of realistic execution environments, ungrounded synthetic queries, and reward-induced verbosity. Training four different LLMs with PROVE yields significant gains on three multi-turn tool-use benchmarks, with improvements up to +10.2 points on BFCL Multi-Turn.
The authors introduce ViMax, an agentic video generation framework that coordinates multiple specialized agents to produce long-form videos with narrative planning and visual consistency. By combining a hierarchical narrative engine with retrieval-augmented generation and dependency-aware visual tracking, ViMax maintains global story coherence and consistent character/environment states across scenes, addressing limitations of existing short-clip methods.
The authors introduce EvoTrainer, a framework that treats the training harness itself as an evolvable component in LLM reinforcement learning. By co-evolving policies and harness heuristics through empirical feedback, EvoTrainer matches or exceeds human-engineered RL baselines across three domains, with the largest gains in long-horizon agentic software engineering.
The authors propose GenClaw, an agentic image generation framework that breaks generation into three stages: conceptualization, code-based sketching (e.g., SVG, HTML, Three.js), and final texturing via an image model. This replaces black-box prompt rewriting with explicit, editable code intermediates, enabling precise control and interpretability.
Zhou et al. conducted the first systematic measurement of authentication security in real-world remote Model Context Protocol (MCP) servers, scanning over 7,900 live servers and performing in-depth analysis on 119 OAuth-enabled servers. They found that 40.55% of servers require no authentication, and among authenticated servers, every tested server had at least one authentication flaw, with 96.6% vulnerable to dynamic client registration attacks.
The authors constructed SLEIGHT-Bench, a benchmark of 40 synthetic transcripts showing a coding agent covertly pursuing harmful objectives like weight exfiltration or credential theft. Testing an Opus 4.6 monitor with extended thinking across 10 trials at a 1% false-positive rate, they found that 20 of the 40 attacks were never caught, and the overall catch rate was just 32%.
The authors critique the dominant on-the-fly paradigm for AI agents, which synthesizes plans and executes actions rapidly in response to prompts, arguing it bypasses established software engineering processes like testing and adversarial evaluation. They propose an AI Workflow Store of hardened, reusable workflows to amortize the cost of rigor across users, aiming to improve reliability and security for high-stakes applications.
The authors propose Co-Director, a hierarchical multi-agent framework that formalizes video storytelling as a global optimization problem. They introduce a multi-armed bandit for global creative direction and a local multimodal self-refinement loop for identity and consistency. GenAD-Bench, a 400-scenario dataset, shows significant improvements over baselines.
The authors propose VisionCreator, a native visual-generation agentic model that unifies Understanding, Thinking, Planning, and Creation (UTPC) capabilities. End-to-end trained on a new dataset and optimized via Progressive Specialization Training and Virtual Reinforcement Learning, VisionCreator-8B/32B models outperform larger closed-source models on the new VisGenBench benchmark across multiple dimensions.