9 papers indexed here
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.
ContextEvo, a framework that learns a context policy from long-horizon trajectories and reconstructs the model-visible context at key decision points, identifies context-related failures, and applies targeted policy updates, is introduced.
This work introduces Executable Semantic Commitments with Clean-Room Recovery (ESC-CR), a policy-backed framework for secure inter-agent code generation and recovery that preserves evidence-backed claims while suppressing unauthorized releases under matched computational budgets.
The selection-invariant communication compiler (SICC), which constrains this post-authorization representation kernel rather than prescribing templates, is introduced, which proves a compositional communication-layer guarantee.
EvoRS is introduced, a self-evolving RL framework that evolves the reward system from on-policy experience, representing it as an executable Reward-DAG, and is updated from on-policy rollouts and reward traces to maintain train-time reliability.
Convergent Detour Hijacking is introduced, a text-only, runtime-independent attack that couples selection manipulation, malicious skill instructions, and tool-chain resource amplification largely separately and evaluates it across multiple LLM backends and 491 held-out tasks under single-task and multi-turn conditions.
CapLease is introduced, an authorization-consumption layer that follows proposal- and authority-level defenses, binds an authenticated user confirmation to a canonical action, and enforces transactional Issue-Prepare-Commit transitions, which identifies durable authorization state, rather than token representation alon...
Minimum-Necessary Communication is introduced, a typed semantic-declassification protocol that selects a task-sufficient disclosure from an application-authored candidate family and binds it to explicit recipient, purpose, forwarding, lifetime, logging, and memory scopes.
SWE-Bench ProMax is introduced, an expert-curated, multilingual code refactoring benchmark of 170 instances drawn from real commits across seven programming languages, which presents a meaningful and unsaturated challenge for current AI coding agents.
HarnessLens is introduced, a budget-aware framework for automated harness evolution that jointly explores the task space and user-configurable components, derives candidate modifications from execution trajectories, and selectively verifies each candidate on behavior-relevant tasks using an attributable-evidence gate.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
