We have 5 of 13 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.
Long-horizon agents learn from failure, but the value of a failure record can change as execution progresses. We study when retaining, compressing, or removing the same history block improves subsequent execution relative to full-history KEEP. We introduce RECAP, a framework that combines matched context interventions,...
Online agents can improve future service by constructing reusable tools, guidance, or model states, but this work competes with current requests for the same GPUs. Exploiting idle compute for self-evolution faces a fundamental systems constraint: benefits arrive only after an artifact is published and used, while pausi...
This work forms external-policy evolution under these two budgets and introduces SkillSmith, a conflict-driven learning system that improves over EvoSkill over OfficeQA and SealQA, and sustains improvement beyond SkillClaw on WildClawBench.
Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache. Yet today's"forget"operations delete a plaintext memory record and stop, leaving every artifact derived from the revoked information intact. We f...
A reference-free judge is formalized as a latent solver, and a closed-form bound on discriminability (ROC-AUC) in the judge's competence and answer-space size is yields the result that the marginal AUC is confounded by item difficulty while a within-question estimator is not.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
