TAPO: Transition-Aware Policy Optimization for LLM Agents
An AI research paper on TAPO: Transition-Aware Policy Optimization for LLM Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
aipentium - AI Papers with Code, Datasets and Engineering Notes
aipentium: browse curated AI and robotics papers about humanoid robots, embodied AI, robot manipulation, VLA models, Diffusion Policy, Sim2Real and robot foundation models.
RepBench: Compiling Benchmarks into Capability Representations for Large Language Models
An AI research paper on RepBench: Compiling Benchmarks into Capability Representations for Large Language Models.
Engineering 5.0 · Research 7.0 · Business 4.0
Flux-OPD: On-Policy Distillation with Evolving Contexts
An AI research paper on Flux-OPD: On-Policy Distillation with Evolving Contexts.
Engineering 5.0 · Research 7.0 · Business 4.0
DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness
An AI research paper on DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness.
Engineering 5.0 · Research 7.0 · Business 4.0
SKILL-KD: Contrastive Skill Distillation for LLM Agents
An AI research paper on SKILL-KD: Contrastive Skill Distillation for LLM Agents.
Engineering 5.0 · Research 7.0 · Business 4.0
Group-Reflective Self-Distillation for Agentic Reinforcement Learning
An AI research paper on Group-Reflective Self-Distillation for Agentic Reinforcement Learning.
Engineering 5.0 · Research 7.0 · Business 4.0
An Instrument to Evaluate Governance Proposals: AI Policy Analysis at Scale
An AI research paper on An Instrument to Evaluate Governance Proposals: AI Policy Analysis at Scale.
Engineering 5.0 · Research 7.0 · Business 4.0
Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training
An AI research paper on Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training.
Engineering 5.0 · Research 7.0 · Business 4.0
Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game
An AI research paper on Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game.
Engineering 5.0 · Research 7.0 · Business 4.0
Vibe-FDTR: An agent-oriented framework for reproducible frequency-domain thermoreflectance data analysis
An AI research paper on Vibe-FDTR: An agent-oriented framework for reproducible frequency-domain thermoreflectance data analysis.
Engineering 5.0 · Research 7.0 · Business 4.0
LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency
An AI research paper on LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency.
Engineering 5.0 · Research 7.0 · Business 4.0
Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation
An AI research paper on Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation.
Engineering 5.0 · Research 7.0 · Business 4.0
MemHarness: Memory Is Reconstructed, Not Replayed
An AI research paper on MemHarness: Memory Is Reconstructed, Not Replayed.
Engineering 5.0 · Research 7.0 · Business 4.0
CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance
An AI research paper on CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance.
Engineering 5.0 · Research 7.0 · Business 4.0
From Textual Requirements to Microservice Architectures - A Comprehensive Evaluation of LLM-Based Design Synthesis
An AI research paper on From Textual Requirements to Microservice Architectures - A Comprehensive Evaluation of LLM-Based Design Synthesis.
Engineering 5.0 · Research 7.0 · Business 4.0
ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding
An AI research paper on ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding.
Engineering 5.0 · Research 7.0 · Business 4.0
PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?
An AI research paper on PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?.
Engineering 5.0 · Research 7.0 · Business 4.0
When Specifications Conflict: A Symmetry-Based Framework for Measuring LLM Preferences
An AI research paper on When Specifications Conflict: A Symmetry-Based Framework for Measuring LLM Preferences.
Engineering 5.0 · Research 7.0 · Business 4.0
When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence
An AI research paper on When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence.
Engineering 5.0 · Research 7.0 · Business 4.0
A foundation model of numerical intelligence with cross-disciplinary generalization
An AI research paper on A foundation model of numerical intelligence with cross-disciplinary generalization.
Engineering 5.0 · Research 7.0 · Business 4.0