We have 8 of 27 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on this, skill evolution iteratively improves skills using execution feedback. However, improvement may require several interdependent edits, so low-reward versions can sti...
Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities. However, enabling multimodal agents to continually acquire useful information from complex, heterogeneous multimodal data remains a signif...
This work introduces EAVer, an End-to-end Agentic Verifier that learns to control the complete response-level verification workflow as a unified policy, and construct 794 bidirectional same-trajectory preference pairs that keep claim grouping, search, and evidence fixed, enabling decision-focused Direct Preference Opti...
XBRIDGE is proposed, a decode-free communication protocol that outperforms text-based communication on all seven tasks for each model pair while achieving 11x lower latency, and in a same-architecture setting it also exceeds a KV-sharing baseline on six of seven tasks.
MEMPROBE is the first benchmark to study memory recovery directly, reconstructing the user state a system retains and scoring it against ground truth, and is seen as a step toward an environment where agents are trained to remember their users, growing more faithful the longer they know them.
A systematic analysis of expert routing patterns in MoE models reveals Language Routing Isolation, in which high- and low-resource languages tend to activate largely disjoint expert sets, and proposes RISE, a framework that exploits routing isolation to identify and adapt language-specific expert subnetworks.
A controlled harness evaluation of memory substrates for memory-augmented agents, covering dense and sparse indices, text records, structural stores, hierarchical stores, refinement-based memories, parametric updates, and activation-compatible context mechanisms, shows that no single substrate consistently dominates.
This work proposes HyperSkill, a hypergraph-based memory framework that jointly improves what to store, how memory is structured and retrieved, and how memory evolves, and represents memory as a hypergraph with two node types, subtask steps and reusable skills.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
