Found 4,326 document(s)
Page 19 of 289
-
Language-model agents increasingly solve complex tasks through parallel reasoning and asynchronous information gathering. Controlled replay across two model families and three benchmarks shows that delivery timing redire...
-
Recursive self-improvement (RSI) requires agents to diagnose system bottlenecks and coordinate improvements across training and inference. We refer to the agents' capability to jointly optimize training data, the trainer...
-
The continuous evolution of next-generation power systems, characterized by the high penetration of renewable energy resources and dynamic topology variations, poses formidable challenges to traditional N-1/N-2 contingen...
-
Blurred vehicle contours and low contrast limit detection performance in infrared remote sensing imagery, while existing fusion methods may introduce polarization noise and fail to integrate complementary information eff...
-
In agent workflows, a brief human instruction can alter subsequent search, reasoning, and tool execution, yet final task outcomes rarely reveal the contribution of an individual instruction to human-agent joint productio...
-
Coding agents increasingly undertake development tasks in mature enterprise repositories, yet existing benchmarks offer limited insight into whether they fulfill complete Product Requirement Documents (PRDs) and where de...
-
Document understanding is increasingly judged on where an answer comes from, scored against annotated gold locations as if each fact lived in one place. In long visual documents, a fact often lives in several places: a c...
-
Much of the manipulation in influencer content is not false but disproportionate, framing accurate facts as historic, urgent, or catastrophic. Existing approaches either verify factual claims or detect clickbait and prop...
-
Rubric-based reinforcement learning (RL) trains policies for open-ended generation with natural-language criteria as rewards, but these rewards can become ineffective as training progresses. We identify two failure modes...
-
Large language model (LLM) agents now trade real capital using news as evidence, yet they cannot reliably tell fabricated headlines from real news. Because they read the same feeds under near-identical policies, a single...
-
E-commerce decisions require applying natural-language rules to the available case evidence. We introduce WenSight-Decision-1, a shared model that scores supplied options directly from rules and case information for six ...
-
Text-to-image diffusion models can produce unsafe content, while output filtering intervenes only after synthesis. We investigate whether native generation signals enable early detection of unsafe and adversarial inputs....
-
Human-collected robot manipulation data often mix successful behavior with retries, pauses, recoveries, and failures. Advantage-Conditioned Behavior Cloning (AC-BC) can exploit such mixed-quality data, but only if the co...
-
Large language models (LLMs) are increasingly used to generate Verus contracts for Rust programs together with the proofs that establish them. Yet verifier acceptance, the common measure of success, shows only that the i...
-
Reinforcement learning for computer-use agents increasingly relies on proactive reward agents that interact with the post-execution GUI environment to verify what recorded screenshots cannot reveal. The reliability of su...