SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
hub Canonical reference
Autogen: Enabling next-gen llm applications via multi-agent conversations
Canonical reference. 94% of citing Pith papers cite this work as background.
26
Pith papers citing it
Background
94% of classified citations
hub tools
citation-role summary
background 15
other 1
citation-polarity summary
years
2026 26representative citing papers
IDS is an agentic LLM system that incrementally synthesizes both implementation and proof for distributed key-value stores, succeeding on all 7 specs where prior agents succeeded on only 2.
AstraFlow decouples RL components into autonomous dataflow services to natively support multi-policy agentic LLM training, elastic scaling, and cross-region execution with 2.7x speedup on math, code, search, and AgentBench workloads.
FlowSteer is a prompt-only attack that biases multi-agent LLM workflow planning to propagate malicious signals, raising success rates by up to 55%, with FlowGuard as an input-side defense reducing it by up to 34%.
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.
EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.
ClawMark is a new benchmark for multi-turn multi-day multimodal coworker agents in stateful evolving services, with deterministic Python checkers showing frontier models achieve only 20% strict task success.
The first systematization of blockchain-based agent-to-agent payments organizes designs into discovery, authorization, execution, and accounting stages while identifying trust and security gaps.
DecentMem is a decentralized dual-pool memory framework for self-evolving multi-agent systems that provides O(log T) regret guarantees and yields up to 23.8% accuracy gains over centralized baselines.
RMA, a multi-agent system with structured memory and iterative feedback loops, solves 8 out of 10 research-level math problems on the new First Proof benchmark and outperforms GPT-5.2R and Aletheia according to expert evaluation.
LEMON trains an LLM orchestrator with counterfactual-augmented GRPO to produce deployable multi-agent specifications that reach state-of-the-art results on six reasoning and coding benchmarks.
STAR presents a failure-aware routing framework using a state-conditioned transition policy and an agent routing matrix combining expert routes with learned recoveries from execution traces to improve multi-agent spatiotemporal reasoning.
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
A critique-and-routing controller cast as a finite-horizon MDP with policy-gradient optimization outperforms one-shot routing baselines on reasoning benchmarks while using the strongest agent for under 25% of calls.
HMACE deploys Proposer, Generator, Evaluator, and Reflector agents in an evolutionary loop to generate and refine heuristics for NP-hard problems, reporting lower optimality gaps and token costs than baselines on TSP and Online BPP.
FAME models scientific topic trajectories in continuous time to forecast paper impact more accurately than LLMs by aligning manuscripts with field momentum in a dynamic latent space.
LLM agent societies develop power-law coordination cascades and intellectual elites through an integration bottleneck that grows with system size.
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
OptiMat Alloys is a conversational AI system that maintains a living FAIR database of multi-principal element alloy calculations and enables natural-language, on-demand computations with built-in uncertainty checks.
Global Workspace Agents (GWA) is proposed as an active, event-driven cognitive architecture for LLMs featuring an entropy-based intrinsic drive and dual-layer memory to enable sustained self-directed agency.
Argues that trustworthiness in Agent-to-Agent networks requires a new conceptual framework with four design pillars baked in from the beginning, as retrofitting existing single-agent methods is insufficient.
Agentic AI needs social theory as structural priors in the MASS framework to model emergent dynamics from multi-agent interactions.
Skills-Coach optimizes LLM agent skills via task generation, prompt/code tuning, comparative execution, and traceable evaluation, reporting gains on a 48-skill benchmark called Skill-X.
citing papers explorer
-
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
-
Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
IDS is an agentic LLM system that incrementally synthesizes both implementation and proof for distributed key-value stores, succeeding on all 7 specs where prior agents succeeded on only 2.
-
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
AstraFlow decouples RL components into autonomous dataflow services to natively support multi-policy agentic LLM training, elastic scaling, and cross-region execution with 2.7x speedup on math, code, search, and AgentBench workloads.
-
FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
FlowSteer is a prompt-only attack that biases multi-agent LLM workflow planning to propagate malicious signals, raising success rates by up to 55%, with FlowGuard as an input-side defense reducing it by up to 34%.
-
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
-
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.
-
Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.
-
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
ClawMark is a new benchmark for multi-turn multi-day multimodal coworker agents in stateful evolving services, with deterministic Python checkers showing frontier models achieve only 20% strict task success.
-
SoK: Blockchain Agent-to-Agent Payments
The first systematization of blockchain-based agent-to-agent payments organizes designs into discovery, authorization, execution, and accounting stages while identifying trust and security gaps.
-
Self-Evolving Multi-Agent Systems via Decentralized Memory
DecentMem is a decentralized dual-pool memory framework for self-evolving multi-agent systems that provides O(log T) regret guarantees and yields up to 23.8% accuracy gains over centralized baselines.
-
RMA: an Agentic System for Research-Level Mathematical Problems
RMA, a multi-agent system with structured memory and iterative feedback loops, solves 8 out of 10 research-level math problems on the new First Proof benchmark and outperforms GPT-5.2R and Aletheia according to expert evaluation.
-
LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning
LEMON trains an LLM orchestrator with counterfactual-augmented GRPO to produce deployable multi-agent specifications that reach state-of-the-art results on six reasoning and coding benchmarks.
-
STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning
STAR presents a failure-aware routing framework using a state-conditioned transition policy and an agent routing matrix combining expert routes with learned recoveries from execution traces to improve multi-agent spatiotemporal reasoning.
-
The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory
Agentic memory improves clean reasoning but worsens performance when spurious patterns are present in stored trajectories; CAMEL calibration reduces this reliance while preserving clean performance.
-
Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
A critique-and-routing controller cast as a finite-horizon MDP with policy-gradient optimization outperforms one-shot routing baselines on reasoning benchmarks while using the strongest agent for under 25% of calls.
-
HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization
HMACE deploys Proposer, Generator, Evaluator, and Reflector agents in an evolutionary loop to generate and refine heuristics for NP-hard problems, reporting lower optimality gaps and token costs than baselines on TSP and Online BPP.
-
FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution
FAME models scientific topic trajectories in continuous time to forecast paper impact more accurately than LLMs by aligning manuscripts with field momentum in a dynamic latent space.
-
Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems
LLM agent societies develop power-law coordination cascades and intellectual elites through an integration bottleneck that grows with system size.
-
Code as Agent Harness
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
-
OptiMat Alloys: a FAIR, living database of multi-principal element alloys enabled by a conversational agent
OptiMat Alloys is a conversational AI system that maintains a living FAIR database of multi-principal element alloy calculations and enables natural-language, on-demand computations with built-in uncertainty checks.
-
"Theater of Mind" for LLMs: A Cognitive Architecture Based on Global Workspace Theory
Global Workspace Agents (GWA) is proposed as an active, event-driven cognitive architecture for LLMs featuring an entropy-based intrinsic drive and dual-layer memory to enable sustained self-directed agency.
-
Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
Argues that trustworthiness in Agent-to-Agent networks requires a new conceptual framework with four design pillars baked in from the beginning, as retrofitting existing single-agent methods is insufficient.
-
Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems
Agentic AI needs social theory as structural priors in the MASS framework to model emergent dynamics from multi-agent interactions.
-
Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
Skills-Coach optimizes LLM agent skills via task generation, prompt/code tuning, comparative execution, and traceable evaluation, reporting gains on a 48-skill benchmark called Skill-X.
- Counterfactual Trace Auditing of LLM Agent Skills
- SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning