arXiv:2607. 06214v1 Announce Type: new Abstract: This paper offers a toy framework for considering curiosity as an ecosystem.
This paper offers a toy framework for considering curiosity as an ecosystem. First, it suggests that a single agent's inquiry policy (how, when, and why an agent asks a question) depends on how the agent values immediate uncertainty reduction, costs, delayed return, and the value of keeping the question open.
arXiv:2607. 06214v2 Announce Type: replace Abstract: This paper offers a framework for considering curiosity as an ecosystem.
Identifying promising scientific ideas remains an important challenge in research practice. Researchers commonly rely on small-group discussions or one-to-one interactions with a single large language model, yet these approaches often expose them to only a limited range of perspectives and directions.
The article surveys LLM-based agentic reasoning frameworks, presenting a unified formal language that categorizes them into single-agent, tool-based, and multi-agent methods. It reviews application scenarios in scientific discovery, healthcare, software engineering, society, economics, and general-purpose tasks, and compares the distinct features and evaluation strategies of each category. The survey highlights the rapid development of complex agentic systems in real-world contexts.
arXiv:2601.12538v2 Announce Type: replace-cross Abstract: Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) d...
The paper investigates semantic collapse—where AI outputs become less diverse and more similar—within MOLTBOOK, a social network of AI agents steered by human users. Across 30,076 agents, most show reduced diversity over time, but a minority maintain high novelty. Interviews and surveys reveal that sustained novelty is linked to users valuing novelty, providing broad, distinctive material, revising outputs when they narrow, and treating MOLTBOOK as an exploratory world rather than a tool for exploitation.
CORAL is a framework that enables autonomous multi‑agent evolution for open‑ended discovery, replacing rigid heuristics with long‑running agents that explore, reflect, and collaborate via shared memory and asynchronous execution. It incorporates safeguards such as isolated workspaces, evaluator separation, and resource management. In experiments across mathematical, algorithmic, and systems optimization tasks, CORAL achieves 3–10 times higher improvement rates with fewer evaluations than traditional evolutionary baselines, and improves the best known score on Anthropic’s kernel engineering task from 1363 to 1103 cycles.
arXiv:2608. 03283v1 Announce Type: new Abstract: Identifying promising scientific ideas remains an important challenge in research practice.
arXiv:2505. 15998v4 Announce Type: replace Abstract: We present a curiosity-driven AI scientist method for discovering system-level dynamics in Flow-Lenia, a continuous cellular automaton (CA) with mass conservation and parameter localization.
ExplorationBench is a benchmark designed to evaluate AI systems’ ability to conduct scientific exploration in verifiable alien worlds, where rules are executable and can be precisely checked. It consists of two sandboxes—AlienCode and AlienLogic—each offering discovery targets, tasks, flawed manuals, environmental feedback, and tool‑call schemas. The benchmark tests whether systems can generate new hypotheses, design experiments, and iterate on results, rather than merely recalling pre‑trained knowledge, and finds that top performers can acquire and apply unfamiliar rules, though performance varies across exploration trajectories.
ExplorationBench is a new benchmark designed to evaluate AI systems’ ability to conduct scientific exploration in verifiable alien worlds. It comprises two sandbox environments—AlienCode and AlienLogic—each containing discovery targets, tasks, flawed manuals, and tool‑call schemas that force systems to formulate hypotheses, design experiments, and iterate on results. Ten AI systems were tested, revealing that while the best performers can learn and apply unfamiliar rules, their progress varies across exploration trajectories and can even regress with continued exploration.