Category: agents
-
Apodex-1.0: deep research as multi-agent verification
TLDR: Apodex-1.0 is most interesting as a verification-centric agent-system design: independent subagents explore, a shared report pool accumulates evidence, and verifier agents audit claims from outside the worker trace.
-
Graph of Agents: multi-agent value comes from information flow
TLDR: Graph of Agents is useful because it treats collaboration as a test-time graph problem: choose relevant agents, score their answers, pass messages in the right direction, and pool the result.
-
SkillOpt: training the procedure outside the weights
TLDR: SkillOpt treats an agent skill as an optimizable text artifact. The model stays frozen, rollouts provide evidence, an optimizer proposes edits, and a validation gate accepts only real improvements.
-
LeanMarathon: long-horizon formalization as agent engineering
LeanMarathon turns paper-level Lean formalization into a recoverable multi-agent engineering system: blueprint, proof DAG, scoped workers, reviewer issues, and CI gates keep long tasks from drifting.
-
Dynamic Workflows: from prompt to runtime
Dynamic Workflows reframes long-horizon agent work as runtime synthesis: split context, externalize state, verify intermediate outputs, and let the harness carry the parts a single prompt cannot reliably hold.
-
Pi Agent: containerization and compaction
Coding agents need two boundaries at the same time: an execution boundary that controls what they can do, and a context boundary that controls what they can remember across long work.
-
MAS Conference Papers: 近期多智能体系统论文阅读清单
TLDR: This page is a ranked reading shortlist for recent MAS papers, prioritizing collaboration structure, topology design, runtime efficiency, and verification.
-
Beyond Individual Intelligence: the LIFE frame for multi-agent systems
The LIFE survey is useful because it reframes LLM multi-agent systems as a lifecycle: build individual capability, integrate collaboration, attribute failures, and evolve the system.