Related papers: Exact Is Easier: Credit Assignment for Cooperative…

LLM-based multi-agent systems have demonstrated remarkable performance on complex tasks through collaborative reasoning. However, these systems tend to rapidly accumulate extremely long conversation histories during interaction. As…

Large language model (LLM) agents struggle to autonomously evolve coordination strategies in dynamic environments, largely because coarse global outcomes obscure the causal signals needed for local policy refinement. We identify this…

As large language models (LLMs) evolve into sophisticated autonomous agents capable of complex software development tasks, evaluating their real-world capabilities becomes critical. While existing benchmarks like…

AI agents negotiate and transact in natural language with unfamiliar counterparts: a buyer bot facing an unknown seller, or a procurement assistant negotiating with a supplier. In such interactions, the counterpart's LLM, prompts, control…

Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. They can also be used to introduce a diverse group discussion step in chatbot pipelines, enhancing the cultural…

Modern clinical practice relies on evidence-based guidelines implemented as compact scoring systems composed of a small number of interpretable decision rules. While machine-learning models achieve strong performance, many fail to translate…

Large language models (LLMs) are increasingly deployed in agentic systems, where a fundamental task is mapping user intents to relevant external tools. Errors in tool selection can have severe outcomes, such as unauthorized data access,…

The prevalent deployment of Large Language Model agents such as OpenClaw unlocks potential in real-world applications, while amplifying safety concerns. Among these concerns, the self-replication risk of LLM agents driven by objective…

Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We…

We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs. LLM-generated proofs are notoriously correct-but-verbose and brittle across…

As Large Language Models (LLMs) transition from static tools to autonomous agents, traditional evaluation benchmarks that measure performance on downstream tasks are becoming insufficient. These methods fail to capture the emergent social…

The application of Large Language Models (LLMs) in healthcare is expanding rapidly, with one potential use case being the translation of formal medical reports into patient-legible equivalents. Currently, LLM outputs often need to be edited…

Evaluating large language models (LLM) in clinical scenarios is crucial to assessing their potential clinical utility. Existing benchmarks rely heavily on static question-answering, which does not accurately depict the complex, sequential…

Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. However, existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while…

Multi-agent systems have demonstrated the ability to improve performance on a variety of predictive tasks by leveraging collaborative decision making. However, the lack of effective evaluation methodologies has made it difficult to estimate…

Aligning AI systems with organizational decision-making is typically framed as a single-target problem: make the model behave like the organization. We argue this framing obscures a deeper pluralistic challenge. We rely on a decision-policy…

LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of…

Large language model (LLM) agents are increasingly expected to operate in enterprise environments, where work is distributed across specialized roles, permission-controlled systems, and cross-departmental procedures. However, existing…

Multi-agent decision pipelines can outperform single agent workflows when complementarity holds, i.e., different agents bring unique information to the table to inform a final decision. We propose ComplLLM, a post-training framework based…

Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and…