Related papers: Slipstream: Trajectory-Grounded Compaction Validat…

As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution…

Constructing accurate knowledge graphs from long texts and low-resource languages is challenging, as large language models (LLMs) experience degraded performance with longer input chunks. This problem is amplified in low-resource settings…

Long-horizon reasoning in LLM-based agents often fails not from generative weakness but from insufficient verification of intermediate reasoning. Co-Sight addresses this challenge by turning reasoning into a falsifiable and auditable…

We introduce LLM x MapReduce-V3, a hierarchically modular agent system designed for long-form survey generation. Building on the prior work, LLM x MapReduce-V2, this version incorporates a multi-agent architecture where individual…

Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce…

The rapid growth of intelligent connected vehicles (ICVs) and integrated vehicle-road-cloud systems has increased the demand for accurate, real-time HD map updates. However, ensuring map reliability remains challenging due to…

Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment…

Large language models (LLMs) operate within fixed context windows that fundamentally limit conversational continuity. When context fills, compaction discards history irreversibly; when sessions end, all memory resets to zero. Existing…

Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires…

In long conversations, an LLM can produce a next utterance that sounds plausible but rests on premises the conversation has already abandoned. Context-manipulation attacks against deployed agents now actively exploit this gap. We close it…

In recent months, substantial progress has been made in complex reasoning of Large Language Models, particularly through the application of test-time scaling. Notable examples include o1/o3/o4 series and DeepSeek-R1. When responding to a…

The evolution of Large Language Models (LLMs) towards autonomous agents has catalyzed progress in Deep Research. While retrieval capabilities are well-benchmarked, the post-retrieval synthesis stage--where agents must digest massive amounts…

Large language model (LLM) agents increasingly rely on external tools such as search engines to solve complex, multi-step problems, and reinforcement learning (RL) has become a key paradigm for training them. However, the trajectories of…

Resolving real-world software engineering (SWE) issues with autonomous agents requires complex, long-horizon reasoning. Current pipelines are bottlenecked by unoptimized demonstration data, sparse execution rewards, and computationally…

Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result…

Long-context large language models (LC LLMs) combined with retrieval-augmented generation (RAG) hold strong potential for complex multi-hop and large-document tasks. However, existing RAG systems often suffer from imprecise retrieval,…

When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the next attempt and elevating the per-step error rate beyond the base level. This…

Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-intensive scenarios. Moreover, generalization across heterogeneous research settings remains…

As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scientific workflows involving iterative data analysis and hypothesis refinement rapidly…

LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level failure. Existing work frames this as \emph{post-hoc…