Related papers: Slipstream: Trajectory-Grounded Compaction Validat…
Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typically managed through compaction in token space via summarization. However, summarization…
We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing conventional fixed-schedule continuation with real-time, state-conditioned parameter decisions. At…
Retrieval-Augmented Generation (RAG) helps LLMs stay accurate, but feeding long documents into a prompt makes the model slow and expensive. This has motivated context compression, ranging from token pruning and summarization to…
In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…
Large language models generate plausible code but cannot verify correctness. Existing multi-agent systems simulate execution or leave verification optional. We introduce execution-grounded verification as a first-class principle: every code…
Effective incident management in large-scale IT systems relies on troubleshooting guides (TSGs), but their manual execution is slow and error-prone. While recent advances in LLMs offer promise for automating incident management tasks,…
When accelerators fail in modern ML datacenters, operators migrate the affected ML training or inference jobs to entirely new racks. This approach, while preserving network performance, is highly inefficient, requiring datacenters to…
Prompt engineering is crucial for fully leveraging large language models (LLMs), yet most existing optimization methods follow a single trajectory, resulting in limited adaptability, gradient conflicts, and high computational overhead. We…
Accurate prediction of human behavior is crucial for AI systems to effectively support real-world applications, such as autonomous robots anticipating and assisting with human tasks. Real-world scenarios frequently present challenges such…
Optimization has been widely used to generate smooth trajectories for motion planning. However, existing trajectory optimization methods show weakness when dealing with large-scale long trajectories. Recent advances in parallel computing…
State-of-the-art code generation frameworks rely on mental simulation, where LLMs internally trace execution to verify correctness. We expose a fundamental limitation: the Mental-Reality Gap -- where models hallucinate execution traces and…
Efficiently training LLMs with long sequences is important yet challenged by the massive computation and memory requirements. Sequence parallelism has been proposed to tackle these problems, but existing methods suffer from scalability or…
Autonomous agents powered by large language models (LLMs) perform complex tasks through long-horizon reasoning and tool interaction, where a fundamental trade-off arises between execution efficiency and reasoning robustness. Models at…
Many decentralized decision problems require multiple parties to coordinate on shared decisions while keeping objectives, constraints, and data private. Large language models (LLMs) offer a promising way to lower the barrier to…
Autonomous robots operating in dynamic environments must maintain beliefs over a hypothesis space that is rich enough to represent the activities of interest at different scales. This is important both in order to accommodate the…
Large Language Model (LLM) agents often face significant credit assignment challenges in long-horizon, multi-step tasks due to sparse rewards. Existing value-free methods, such as Group Relative Policy Optimization (GRPO), encounter two…
Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative…
LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than discrete tokens,…
Current research on large language model (LLM) agents is fragmented: discussions of conceptual frameworks and methodological principles are frequently intertwined with low-level implementation details, causing both readers and authors to…
Probing studies what information is encoded in a frozen LLM's layer representations by training a lightweight predictor on top of them. Beyond analysis, probes are often used operationally in probe-then-steer pipelines: a learned concept…