1. In recent years, large language models (LLMs) have become increasingly popular in software engineering and have performed well on different programming tasks. However, it is still difficult to know whether these models truly understand pro…

  2. Large Reasoning Models (LRMs) are one of the key components of current agentic systems. LRMs augment their output with an explicit chain-of-thought reasoning stage, introducing a new attack surface for thought injection, in which untrusted…

  3. LLM agents benefit from using memory systems to improve performance on long-horizon, multi-session tasks. However, memory introduces a critical attack surface.

  4. Language agents increasingly use persistent memory to record user preferences and procedures across sessions. We show that memory from benign interactions can cause unsafe or unreliable behavior on later tasks.

  5. AI agents are playing an increasingly important role in physics research. However, existing physics benchmarks only evaluate fixed questions, isolated sub-tasks, or paper reproduction with given solutions, and rarely check research quality…

  6. Why do language models fail on long inputs? The common answer is length.

  7. An autonomous research laboratory could conduct an entire study, from formulating questions to preparing manuscripts. Artificial intelligence (AI) offers one route towards this goal.

  8. Weight-only, lossy quantization substantially reduces the storage and memory requirements for serving large language models (LLMs), but the growing key-value (KV) cache remains a bottleneck for long-context inference on personal devices. W…

  9. Agentic Entity Resolution (ER) systems iteratively plan actions, retrieve evidence, revise hypotheses, and propose graph mutations. An erroneous identity hypothesis may condition later retrieval and produce apparent confirmation.

  10. The rapid progress of software engineering agents drives interest in applying them to open-ended problems such as GPU kernel optimization. However, we find that existing coding agents converge to local optima on real-world, expert-written…

  11. Clinical research over electronic health records depends on derived variables whose definitions sit outside the schema, in item codes, time windows, missingness rules, and output-grain choices that change cohorts and downstream conclusions…

  12. Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manua…

  13. As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are routinely accompanied by comprehensive…

  14. Multi-agent systems (MAS) require both effective coordination and specialized task execution. Existing prompt optimization approaches typically couple these functions within agent-specific prompts.

  15. A coding agent can migrate a machine learning workload, report success, and still change how the model trains. Rising compute costs, limited accelerator capacity, and vendor dependence are pushing organizations toward alternatives to graph…

  16. Large Language Models excel at reasoning and generation but their autoregressive, token-by-token inference makes them unnecessarily slow, expensive, and poorly calibrated for the many routine decisions (routing, gating, scoring, classifica…

  17. Large language models (LLMs) increasingly operate in multi-agent systems where they collaborate by responding to others' choices, creating endogenous feedback loops with vulnerability to social influence, herding behavior and runaway casca…

  18. KV caching reduces the serving cost of large language models (LLMs), but the growing KV cache footprint is increasingly exceeds GPU and host-memory capacity. Therefore, people use SSD to expand the KV cache storage capacity with high I/O b…

  19. Coding-agent benchmarks often describe a task in natural language but grade it with tests taken from the upstream project. Passing those tests can require information the description never states: a constant's name, a module path, an exact…

  20. Agent memory systems such as Mem0 and Zep decide what to keep before any question arrives; coding agents keep the raw history and let the model search it with its own tools. We ask whether designed memory still helps once the model is stro…

  21. Agents are starting to sell to other agents. Seller agents write the listings of tools, services and products, and buyer agents read these listings when they choose what to use.

  22. We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associat…

  23. Repeated Bertrand competition is a stringent benchmark for algorithmic pricing: in homogeneous-goods markets, standard learning procedures typically select the stage-game Nash outcome with prices near marginal cost. We show that LLM pricin…

  24. We placed four Gemini 4 Argon agents in a sandboxed Minecraft survival world and gave them one goal: defeat the Ender Dragon. Each agent controlled a player via an open-source library called Mineflayer and coordinated with its teammates th…

  25. This paper introduces language-based agent control (LBAC), a new programming model for agentic applications that brings techniques from programming languages and language-based security to the problem of agent control. In conventional prog…

  26. Confidence scores determine whether an LLM answer is accepted, reviewed, or regenerated, yet scalar recalibration can only correct errors visible through the score itself. We introduce RADAR (Repair, Adopt, and Diagnose After Recalibration…

  27. Converting verifier outcomes into useful policy updates and partial progress into complete task resolution is crucial for terminal agents. We present Terminal-RSI, which alternates Recursive Self-Rewrite (RSR) of verified trajectories with…