Autonomous Agents

Opening — Why this matters now Functional dependency (FD) discovery has quietly become a victim of its own success. Modern algorithms can enumerate everything—and that is precisely the problem. On realistic schemas, exhaustive FD discovery produces hundreds of thousands of valid dependencies, most of which are technically correct and practically useless. Computationally expensive. Cognitively overwhelming. Operationally irrelevant. ...

Opening — Why this matters now Large language models have learned how to talk. That part is mostly solved. The harder problem—quietly surfacing beneath the hype—is whether they can stay in character. The explosion of role‑playing agents (RPLAs) is not driven by novelty alone. It reflects a structural shift in how humans want to interact with AI: not as tools, but as persistent entities with memory, motivation, and recognizable behavior. When an AI tutor forgets who it is, or a game NPC contradicts its own values mid‑conversation, immersion collapses instantly. The paper reviewed here treats that collapse as a technical failure, not a UX quirk—and that framing is overdue. fileciteturn0file0 ...

Opening — Why this matters now Multimodal models have become unnervingly confident readers of documents. Hand them a PDF, a scanned exam paper, or a photographed worksheet, and they will happily extract text, diagrams, and even implied structure. The problem is not what they can read. It is what they refuse to unread. In real classrooms, mathematics exam papers are not pristine artifacts. They are scribbled on, folded, stained, partially photographed, and occasionally vandalized by enthusiastic graders. Yet most document benchmarks still assume a polite world where inputs are complete and legible. This gap matters. An AI system that confidently invents missing math questions is not merely wrong—it is operationally dangerous. ...

Opening — Why this matters now Tool-using agents are no longer a novelty. They are quietly becoming the default interface between LLMs and the real world: APIs, databases, search engines, execution environments. Yet most reinforcement learning pipelines still behave as if every step in a trajectory deserves the same bonus. That assumption was tolerable when tasks were short. It collapses when agents think, call tools, fail, retry, and recover over ten or more turns. ...

Opening — Why this matters now Everyone is chasing longer context windows. Million-token prompts. Endless chat logs. The assumption is simple: if the model can see everything, it will remember correctly. This paper shows why that assumption fails. In long-horizon, goal-driven interactions, errors rarely come from missing information. They come from retrieving the wrong information—facts that are semantically similar but contextually incompatible. Bigger windows amplify the problem. Noise scales faster than relevance. ...

Opening — Why this matters now Architectural studios are quietly changing. Not with robotic arms or parametric scripts, but with prompts. Text-to-image models now sit beside sketchbooks, offering instant massing ideas, stylistic variations, and visual shortcuts that once took hours. The promise is obvious: faster ideation, lower friction, fewer blank pages. The risk is less visible. When creativity is partially outsourced, what happens to confidence, authorship, and cognitive effort? ...

Opening — Why this matters now Genomics QA is no longer a toy problem for language models. It sits at the uncomfortable intersection of messy biological databases, evolving schemas, and questions that cannot be answered from static training data. GeneGPT proved that LLMs could survive here—barely. This paper shows why surviving is not the same as scaling. ...

Opening — Why this matters now Reasoning models are having a moment. Latent-space architectures promise to outgrow chain-of-thought without leaking tokens or ballooning costs. Benchmarks seem to agree. Some of these systems crack puzzles that leave large language models flat at zero. And yet, something feels off. This paper dissects a flagship example—the Hierarchical Reasoning Model (HRM)—and finds that its strongest results rest on a fragile foundation. The model often succeeds not by steadily reasoning, but by stumbling into the right answer and staying there. When it stumbles into the wrong one, it can stay there too. ...

Opening — Why this matters now Multi-agent AI is no longer a lab curiosity. Tool-using LLM agents already negotiate, cooperate, persuade, and sometimes sabotage—often without humans in the loop. What looks like “emergent intelligence” at first glance is, more precisely, a set of interaction effects layered on top of massive pre-trained priors. And that distinction matters. Traditional multi-agent reinforcement learning (MARL) gives us a language for agents that learn from scratch. LLM-based agents do not. They arrive already socialized. ...

Opening — Why this matters now Most AI control systems are still designed around a brittle assumption: either the agent satisfies everything, or the problem is declared unsolvable. That logic collapses quickly in the real world. Robots run out of battery. Services compete for shared resources. Environments act adversarially, not politely. In practice, goals collide. ...