-
Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user behavior, and upstream models shift, the choices governing retrieval, ranking, and serving…
-
Competitive Market Behavior of LLMs (arxiv.org) discussed ↗ 10w
Large language models (LLMs) are increasingly deployed as economic agents, yet there is little evidence whether LLM agents are suited for participating in market mechanisms designed for humans, and whether these mechanisms deliver desired…
-
LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic features can be an unreliable lens for understanding intern…
-
Many production systems can assess a configuration only by using it on live requests and observing noisy feedback. Modern agentic systems are a prominent example, with inference-time choices such as model selection, retrieval depth, prompt…
-
A language-model agent asked to analyse an experiment will usually return working code. Whether the analysis is defensible is a different question.
-
Fleets of LLM agents now externalize effects that cannot be fully undone: they move money, deploy code, delete data, and disclose information. Current controls check one effect at a time, so a fleet of individually authorized agents can ov…
-
Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the note fails to record. The standard check is an LLM judge: a second model reads the note aga…
-
How Proper Scoring Rules Shape LLM Forecasting (arxiv.org) discussed ↗ 11w
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…
-
Sliding-window beats linear attention (arxiv.org) discussed ↗ 11w
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…
-
LLMs Can Design Near-Optimal OR Algorithms (arxiv.org) discussed ↗ 11w
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…
-
SKILL.state: Scalable Long-Horizon Agent Skills (arxiv.org) discussed ↗ 11w
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…
-
AI Agents Push Humans Out of the Loop (arxiv.org) discussed ↗ 11w
AI agents pose significant risks as they are granted increasing autonomy. A commonly proposed solution is human oversight and keeping a ''human in the loop'', but this is not a simple solution: Not only do current approaches to AI agent de…
-
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…
-
A lot of prior work addressed key-value (KV) cache selection and compression by sparse attention to enable long-context inference for transformer language models without excessive hardware budgets. We provide a new method for fine-tuning m…
-
Active Inference as Context Acquisition for AI Agents (arxiv.org) discussed ↗ 12w
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…
-
EnvHarness: Awakening Static Worlds for Agent Learning (arxiv.org) discussed ↗ 12w
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-…
-
AutoResearch: Insight In, Hallucination Out (arxiv.org) discussed ↗ hallucination 12w
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…