Related papers: Towards Structured, State-Aware, and Execution-Gro…
The rise of Large Reasoning Models (LRMs) signifies a paradigm shift toward advanced computational reasoning. Yet, this progress disrupts traditional agent frameworks, traditionally anchored by execution-oriented Large Language Models…
Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial…
The development of LLMs has elevated AI agents from task-specific tools to long-lived, decision-making entities. Yet, most architectures remain static and reactive, tethered to manually defined, narrow scenarios. These systems excel at…
Binary analysis increasingly relies on large language models (LLMs) to perform semantic reasoning over complex program behaviors. However, existing approaches largely adopt a one-pass execution paradigm, where reasoning operates over a…
Software Development (SD) is remarkably dynamic and is critically dependent on the knowledge acquired by the project's software developers as the project progresses. Software developers need to understand large amounts of information…
Structured state space sequence (S4) models have recently achieved state-of-the-art performance on long-range sequence modeling tasks. These models also have fast inference speeds and parallelisable training, making them potentially useful…
Embodied agents operating in multi-agent, partially observable, and decentralized environments must plan and act despite pervasive uncertainty about hidden objects and collaborators' intentions. Recent advances in applying Large Language…
Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of past decisions. Current agent memory systems and database paradigms treat memory as…
Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…
Software Engineering Agents (SWE-Agents) have proven effective for traditional software engineering tasks with accessible codebases, but their performance for embodied tasks requiring well-designed information discovery remains unexplored.…
Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and…
The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory…
In Text-to-SQL, execution feedback is essential for guiding large language models (LLMs) to reason accurately and generate reliable SQL queries. However, existing methods treat execution feedback solely as a post-hoc signal for correction…
Agents based on large language models have recently shown strong potential on real-world software engineering (SWE) tasks that require long-horizon interaction with repository-scale codebases. However, most existing agents rely on…
Strategic reasoning enables agents to cooperate, communicate, and compete with other agents in diverse situations. Existing approaches to solving strategic games rely on extensive training, yielding strategies that do not generalize to new…
The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs…
Autonomous software agents operating in dynamic environments need to constantly reason about actions in pursuit of their goals, while taking into consideration norms which might be imposed on those actions. Normative practical reasoning…
As humans, we are natural any-horizon reasoners, i.e., we can decide whether to iteratively skim long videos or watch short ones in full when necessary for a given task. With this in mind, one would expect video reasoning models to reason…
Large language model (LLM)-powered agents have demonstrated strong capabilities in automating software engineering tasks such as static bug fixing. However, in the real world, the development of mature software is typically predicated on…
We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…