ClawForge is a generator framework that creates reproducible executable benchmarks for command-line agents under state conflict, with ClawForge-Bench showing frontier models reach at most 45.3% strict accuracy and that state inspection drives most performance gaps.
Canonical reference
Agent0 -vl: Exploring self -evolving agent for tool -integrated vision -language reasoning
Canonical reference. 80% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
80% of classified citations
citation-role summary
background 4
method 1
citation-polarity summary
years
2026 12representative citing papers
TRACER attaches verifiable sentence-level provenance records to multimodal agent outputs using tool-turn alignment and semantic relations, yielding 78.23% answer accuracy and fewer tool calls than baselines on TRACE-Bench.
RewardHarness self-evolves a tool-and-skill library from 100 preference examples to reach 47.4% accuracy on image-edit evaluation, beating GPT-5, and yields stronger RL-tuned models.
A modular 8B agent with episodic visual memory and RL-trained retrieval reaches 91.4% cross-turn image recall over 20 turns, outperforming 32B all-context baselines with ~1.8× lower latency.
TACO combines Differential Answer-Probe Reward (DAPR) and Outcome-Gated Advantage Routing (OGAR) to assign credit to tool calls in agentic visual reasoning, producing accuracy gains on multimodal benchmarks.
VISE is an unsupervised self-evolving method for LMMs that uses invariance rewards to improve visual conditioning, reporting gains on captioning and reduced hallucination across multiple models.
MetaDesigner is a self-correcting LLM system that automates full metasurface design pipelines for complex tasks such as RGB metalenses and full-color holograms.
Seirênes trains LLMs via adversarial self-play to generate and overcome evolving distractions, producing gains of 7-10 points on math reasoning benchmarks and exposing blind spots in larger models.
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
E² uses transport-regularized sparse control on learned reverse-time SDEs with topology-driven selection and Topological Anchoring to generate realistic adversarial scenarios, improving collision discovery by 9.01% on nuScenes and up to 21.43% on nuPlan while enabling closed-loop robustness gains.
SimpleMem proposes semantic structured compression, online synthesis, and intent-aware retrieval to create efficient lifelong memory for LLM agents, reporting 26.4% F1 gains and up to 30x lower token use on LoCoMo benchmarks.
Position paper identifies structural challenges in applying generic agentic AI to Earth Observation and outlines design principles for EO-native agents focused on geospatial state and validity.
citing papers explorer
-
ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents
ClawForge is a generator framework that creates reproducible executable benchmarks for command-line agents under state conflict, with ClawForge-Bench showing frontier models reach at most 45.3% strict accuracy and that state inspection drives most performance gaps.
-
TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents
TRACER attaches verifiable sentence-level provenance records to multimodal agent outputs using tool-turn alignment and semantic relations, yielding 78.23% answer accuracy and fewer tool calls than baselines on TRACE-Bench.
-
RewardHarness: Self-Evolving Agentic Post-Training
RewardHarness self-evolves a tool-and-skill library from 100 preference examples to reach 47.4% accuracy on image-edit evaluation, beating GPT-5, and yields stronger RL-tuned models.
-
Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing
A modular 8B agent with episodic visual memory and RL-trained retrieval reaches 91.4% cross-turn image recall over 20 turns, outperforming 32B all-context baselines with ~1.8× lower latency.
-
TACO: Tool-Augmented Credit Optimization for Agentic Tool Use
TACO combines Differential Answer-Probe Reward (DAPR) and Outcome-Gated Advantage Routing (OGAR) to assign credit to tool calls in agentic visual reasoning, producing accuracy gains on multimodal benchmarks.
-
Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models
VISE is an unsupervised self-evolving method for LMMs that uses invariance rewards to improve visual conditioning, reporting gains on captioning and reduced hallucination across multiple models.
-
Agentic metasurface design with self-correcting language-model systems
MetaDesigner is a self-correcting LLM system that automates full metasurface design pipelines for complex tasks such as RGB metalenses and full-color holograms.
-
Seir\^enes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
Seirênes trains LLMs via adversarial self-play to generate and overcome evolving distractions, producing gains of 7-10 points on math reasoning benchmarks and exposing blind spots in larger models.
-
LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
-
Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles
E² uses transport-regularized sparse control on learned reverse-time SDEs with topology-driven selection and Topological Anchoring to generate realistic adversarial scenarios, improving collision discovery by 9.01% on nuScenes and up to 21.43% on nuPlan while enabling closed-loop robustness gains.
-
SimpleMem: Efficient Lifelong Memory for LLM Agents
SimpleMem proposes semantic structured compression, online synthesis, and intent-aware retrieval to create efficient lifelong memory for LLM agents, reporting 26.4% F1 gains and up to 30x lower token use on LoCoMo benchmarks.
-
Agentic AI for Remote Sensing: Technical Challenges and Research Directions
Position paper identifies structural challenges in applying generic agentic AI to Earth Observation and outlines design principles for EO-native agents focused on geospatial state and validity.