arXiv Machine Learning
Aug 4
Asleep at the Wheel: JEPA's Limitations in Evaluating Novel Driving Data
arXiv:2608. 01336v1 Announce Type: cross Abstract: Modern autonomous-driving fleets record far more video than human reviewers can inspect.
AI agents
Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv Machine Learning
Aug 4
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
arXiv:2608. 01918v1 Announce Type: new Abstract: Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable environments.
arXiv Machine Learning
Aug 4
AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving
arXiv:2608. 00881v1 Announce Type: new Abstract: Large language model agents increasingly act through stateful tools, yet model generation and environment execution remain serialized at every step.
arXiv Machine Learning
Aug 4
Inference-Time Policy Alignment for Fair Reinforcement Learning
arXiv:2608. 00175v1 Announce Type: new Abstract: Deep reinforcement learning (RL) agents achieve strong performance by optimizing scalar reward functions.
arXiv Machine Learning
Aug 4
The Condition-Number Barrier in Sparse Least Squares
arXiv:2608. 02588v1 Announce Type: cross Abstract: In [AS21], Axiotis and Sviridenko conjectured that the linear dependence on the restricted condition number in sparse convex optimization cannot be improved by a polynomial-time algorithm.
arXiv Machine Learning
Aug 4
MemoryForge: Synthesize Lifelong Memory for Human-Like LLM Agents
arXiv:2608. 00007v1 Announce Type: cross Abstract: Equipping Large Language Models (LLMs) with human-like personas is crucial for agentic applications, such as role-play and user simulation.
arXiv Machine Learning
Aug 4
From Information to Delegation: Mapping Human-AI Financial Decision Making
arXiv:2608. 02100v1 Announce Type: cross Abstract: As AI increasingly participates in human decision making, understanding how decision-making authority is distributed between humans and AI has become a fundamental behavioural question.
arXiv Machine Learning
Aug 4
FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds
arXiv:2608. 01049v1 Announce Type: cross Abstract: World models have attracted significant attention for their ability to capture and predict the structure and dynamics of the physical world.
arXiv Machine Learning
Aug 4
Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning
arXiv:2505. 08630v2 Announce Type: replace Abstract: Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL).
Hugging Face Trending Papers
Aug 3
FLARE: Few-shot Learning-based Adaptive Reflective Engine
Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-of-the-art optimizers like GEPA (Genetic-Pareto) have argued that reflective instruction evolution can outperform traditional reinforcement learning and few-shot optimization.
Hugging Face Trending Papers
Aug 3
Quo Vadis, World Modeling?
Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural intermediate proxy that allows agents to query lower-cost, more controllable feedback before committing to real actions.
Hugging Face Trending Papers
Aug 3
The Condition-Number Barrier in Sparse Least Squares
In [AS21], Axiotis and Sviridenko conjectured that the linear dependence on the restricted condition number in sparse convex optimization cannot be improved by a polynomial-time algorithm. We establish their conjectured lower bound for least-squares objectives, conditional on the randomized exact-volume Small-Set Expansion Hypothesis in the weighted regular-graph formulation of Raghavendra, Steurer, and Tulsiani [RST12].
Hugging Face Trending Papers
Aug 3
Abduction Without a Body? Representational Grounding and the Abduction Loop for Scientific Hypothesis Generation
Can scientific abduction occur without continuous sensorimotor embodiment? Recent arguments in AI and philosophy of science hold that genuine hypothesis generation requires an agent continuously coupled to the physical world.
Microsoft Research
Aug 3
Orchard: An open framework for scalable agentic AI
Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure.
Towards Data Science
Aug 3
How to Build CLI Agents with Python & Ollama
Create a local CLI Agent from scratch completely for free The post How to Build CLI Agents with Python & Ollama appeared first on Towards Data Science .
Hugging Face Trending Papers
Aug 3
Self-Certification of Representation Adequacy: Sequential Certification at Minimum Task Loss
Agents that act on a compressed representation of their history face a structural risk: if the representation aliases histories with different optimal actions, no rule measurable with respect to the representation can avoid an irreducible per-round loss, and the agent may be unable to detect this from its own transcript. This paper develops a four-layer theory of self-certification of representation adequacy.
Hugging Face Trending Papers
Aug 3
Cross-Domain Hybrid OPD for Generalizable Search Agents
Recent advances in Reinforcement Learning (RL) have substantially improved the capabilities of autonomous search agents, enabling sophisticated planning, and iterative retrieval over dynamic information sources. However, optimizing language models for specialized search behaviors often incurs an alignment tax, where gains in search performance come at the expense of general-purpose capabilities, limiting their effectiveness as universal assistants.
Hugging Face Trending Papers
Aug 3
Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents
Search agents now answer questions that take dozens of searches to settle, yet how such an agent reads a page has drawn far less attention than how it finds one. Nearly all of them use one of two document interfaces, and both tie a page to the moment it is opened.
Hugging Face Trending Papers
Aug 3
CompanionBench: A Theory-Anchored, Real-World-Grounded Benchmark for AI Emotional Companionship
LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and prompted simulators, aggregate empathy into one score, and overlook judge biases such as same-family favoritism and scale drift.
Hugging Face Trending Papers
Aug 3
TALSC: Timeliness-Aware Large-Small VLM Collaboration for Infrastructure-Assisted Autonomous Driving
The deployment of Vision-Language Models (VLMs) in autonomous driving (AD) systems is constrained by on-board computing power, restricting vehicles to small VLMs (SVLMs) with limited perception and reasoning capabilities. Infrastructure-assisted AD alleviates this resource constraint by enabling collaboration with large VLMs (LVLMs) at edge servers.