A self-evolving multi-agent catalysis digital twin (CatDT) matches seven gas–solid kinetic benchmarks within ~0.5–2× experiment and computationally proposes non-precious PDH candidates including Ni@ZrO2.
arXiv preprint arXiv:2603.05344 , year=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 10roles
background 2polarities
background 2representative citing papers
Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
Analysis of 13 coding agent scaffolds at pinned commits yields a 12-dimension taxonomy showing five composable loop primitives, with 11 agents combining multiple primitives instead of using one fixed structure.
ProjAgent introduces procedural similarity—retrieving code with matching computational logic—via LLM hidden-state projections, improving repository-level code generation to 41.14% Pass@1 on REPOCOD.
Partial harnesses for LLM agents, specifying only initial execution steps, achieve higher pass rates than fully decomposed workflows, as analyzed through trajectory alignment and validated in synthetic and terminal benchmarks.
A typed-contract harness with containerized 'chambers' and robotics-specific agent skills lets a coding LLM turn a single natural-language prompt into working reproduction, evaluation, and deployment workflows for robot learning.
Coding agents require a three-level proactivity taxonomy (Reactive, Scheduled, Situation Aware) evaluated by insight policy quality using Insight Decision Quality, Context Grounding Score, and Learning Lift.
RSCB-MC is a risk-sensitive contextual bandit memory controller for LLM coding agents that chooses safe actions including abstention, achieving 60.5% proxy success with 0% false positives and low latency in 200-case validation.
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
Under fixed token budget on Circle Packing, deeper per-candidate reasoning beats generating more shallow candidates, and capable models produce evaluation hacks at higher rates.
citing papers explorer
-
Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin
A self-evolving multi-agent catalysis digital twin (CatDT) matches seven gas–solid kinetic benchmarks within ~0.5–2× experiment and computationally proposes non-precious PDH candidates including Ni@ZrO2.
-
Terminal-World: Scaling Terminal-Agent Environments via Agent Skills
Terminal-World is a skill-based synthesis pipeline that generates 5,723 training environments and produces Terminal-World-32B which outperforms baselines on Terminal-Bench 2.0 using only 1.2% of the data.
-
Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
Analysis of 13 coding agent scaffolds at pinned commits yields a 12-dimension taxonomy showing five composable loop primitives, with 11 agents combining multiple primitives instead of using one fixed structure.
-
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
ProjAgent introduces procedural similarity—retrieving code with matching computational logic—via LLM hidden-state projections, improving repository-level code generation to 41.14% Pass@1 on REPOCOD.
-
Harnesses for Inference-Time Alignment over Execution Trajectories
Partial harnesses for LLM agents, specifying only initial execution steps, achieve higher pass rates than fully decomposed workflows, as analyzed through trajectory alignment and validated in synthetic and terminal benchmarks.
-
Nautilus: From One Prompt to Plug-and-Play Robot Learning
A typed-contract harness with containerized 'chambers' and robotics-specific agent skills lets a coding LLM turn a single natural-language prompt into working reproduction, evaluation, and deployment workflows for robot learning.
-
Agentic Coding Needs Proactivity, Not Just Autonomy
Coding agents require a three-level proactivity taxonomy (Reactive, Scheduled, Situation Aware) evaluated by insight policy quality using Insight Decision Quality, Context Grounding Score, and Learning Lift.
-
Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents
RSCB-MC is a risk-sensitive contextual bandit memory controller for LLM coding agents that chooses safe actions including abstention, achieving 60.5% proxy success with 0% false positives and low latency in 200-case validation.
-
PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
-
Effective Harness Engineering for Algorithm Discovery with Coding Agents
Under fixed token budget on Circle Packing, deeper per-candidate reasoning beats generating more shallow candidates, and capable models produce evaluation hacks at higher rates.