This paper evaluates how reward function choice shapes the performance and behavior of LLM forecasters. We compare five proper scoring rules as training objectives for binary forecasts of resolved real-world events.

Post training a language model to reason means updating its weights. Supervised finetuning and reinforcement learning both place the acquired capability inside the model where it cannot be inspected cannot be checked step by step and canno…

• Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards (arxiv.org)

Due to the nature of quadratic attention, Large Language Models (LLMs) consume a lot of memory and energy. Every new token costs more than the previous one.

Cross-lingual alignment in multilingual language models is typically attributed to joint training: shared parameters, mixed-language batches, or explicit alignment objectives. We ask whether monolingual models trained on non-parallel data…

Audits of LLM judges certify a bias by contrasting matched conditions, and the strongest designs difference twice: a within-item contrast between two candidate responses, differenced again across a manipulated attribute, read off a bounded…

We ask whether large language models (LLMs) can design effective algorithms for well-specified operations research (OR) problems. We study inventory control, queueing network control, and assortment optimization.

Industrial control systems (ICSs) rely on programmable logic controllers (PLCs) to connect networked computation with physical control. Tool-using large language model (LLM) agents represent an emerging attack threat: can an autonomous age…

Large Language Models (LLMs) increasingly act as autonomous agents executing complex, long-running procedural skills. Existing agent runtimes maintain execution by continually appending observations, actions, and intermediate reasoning tra…

Large language model agents are increasingly deployed as autonomous loops. Starting from one human goal, such a system repeatedly discovers work, plans, executes tool calls, verifies outcomes and persists state across many unattended itera…

Large language models (LLMs) increasingly assess generated content, giving rise to the LLM-as-a-Judge paradigm. These systems now score outputs, filter content, and gate iterative refinement in production pipelines, where each judgment is…

Collective intelligence can emerge when individuals coordinate through a shared environment, allowing local actions to accumulate into durable social organization. Language-model agents offer a new substrate for this process, yet most mult…

We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal without a central coordinator or scripted pipeline. Agents choo…

Large language model providers are compute constrained, and their universal response to congestion is to degrade service: route queries to smaller models, cut reasoning effort, truncate context. The industry's accounting says this saves mo…

LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interactions and lead to overall task failure. Although external harnesses can substantially improve robustness, harness design remai…

Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture-of-agents synthesis (Wang et al., 2025), while other work finds that interaction adds cos…

Enterprise agent programs are moving from prototypes into production, where reusable skills, tools, and workflow packages must be reviewed with evidence rather than prose. Current gates often scan these artifacts for structure, style, and…

Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a default assumption or spend tokens on a clarifying question, r…

Audited against causal ground truth from executed replay in a single-agent tool environment (ALFWorld), none of the step-level credit signals used to train LLM agents -- LLM-judge scores, outcome-conditioned logprob ratios, or the policy's…

LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While recent environment generation methods attempt to address thi…

Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior overwrites accumulate, mirroring a classical phenomenon in human working memory. Post-…

Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We introduce AutoResearch, a two-stage system that…

Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these method…

Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such pro…

Large language model-based agentic frameworks primarily optimize capability: whether an agent can reason, retrieve information, call tools, delegate work, and complete a goal. Enterprise execution requires a stronger property.

As AI datacenters retire functional GPUs, vast quantities of still capable accelerators enter secondary markets. This paper investigates whether these retired GPUs can find a productive afterlife to form a DumpsterCluster that can serve mo…

Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state. However, the system behavior of these workloads---where latency, cost,…

LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents. At session start, the agent's permissions are set but remain static, and each request is evaluated independently, without considering prio…

When a user question is underspecified, a capable model should recognize that its context is insufficient, identify the missing information, ask for it, and respond only once that information determines a unique answer. We formalize multi-…

Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs. Much of the safety literature studies misaligned LLM behavior through adversarial-elicitation evaluations…

Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving systems. However, existing LLM serving workload studies remain limited in scale and scope.