Web This site Trusted
30 result(s) for “okapi bm25 site hotchips pp site does apache org site www roman com site wiki apache site:arxiv.org” of 32 matched · 1168 ms
Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.
Freshness: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)
The query asks the model to recall the topic of an earlier conversation about Tesla; the gold answer is anchored in one specific session about Pooja’s dig site
from the top result below
https://arxiv.org/html/2608.02613v1
6 Ingest Overhead: When Does Structured Memory Pay Off
https://arxiv.org/html/2608.03048v1
com/JetAstra/PI-Mem
Introduction
The ability to reason over long contexts is increasingly important for large language models (LLMs), supporting applications such as long-document question answering (Gemini Team 2025; Yang et al
https://arxiv.org/html/2501.13956v1
com
Abstract
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark
https://arxiv.org/list/cs.CL/new
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends
https://arxiv.org/list/cs.AI/new
Research artifact available under the Apache-2
https://arxiv.org/html/2407.04974v1
Unlike many existing dec-POMDP-based RL approaches, the proposed algorithm is suitable for model-free multi-agent reinforcement learning as it does not require knowledge of a transition model
https://arxiv.org/html/2407.00762v1
Attackers
I Introduction
II Problem Formulation
II-A Notation
II-B Problem Statement
III Preliminary: Single-Attacker Game
IV Main Results
IV-A Optimization Formulation of a Geometric Solution
IV-B Proof of Equilibrium
V Numerical
https://arxiv.org/html/2407.13076v1
Transmission Parameter Allocation in Multi-Gateway LoRa Networks
I INTRODUCTION
II RELATED WORK
III SYSTEM MODEL
III-A The Traffic Pattern of LoRa Networks
III-B Capture Effect and Quasi-Orthogonality between SFs
III-C Packet Delivery
https://arxiv.org/html/2407.05132v1
Where money does not do its job, Karma achieves socially more desirable resource allocations by being aligned with consumers’ needs rather than their financial power
https://arxiv.org/html/2407.02342v1
org) Wen Chen is with the Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China(e-mail: wenchen@sjtu
https://arxiv.org/html/2309.08431v3
Existing research characterises the losses of LPs, but does not offer tools for strategic liquidity provision
https://arxiv.org/abs/2608.03883
Our systems combine sparse BM25 retrieval, evidence-aware rescoring for self-referential symptom reports, embedding-based reranking, query-prototype expansion, and LLM-based reranking
https://arxiv.org/list/cs.IR/new
Skip to main content
System maintenance August 4th and 5th Learn more ×
Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Information Retrieval
New submissions
Cross-lists
Replacements
See recent
https://arxiv.org/abs/2104.08663
Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs
https://arxiv.org/abs/2608.03860
The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation
https://arxiv.org/list/cs.IR/recent
Skip to main content
System maintenance August 4th and 5th Learn more ×
Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Information Retrieval
Authors and titles for recent submissions
Wed, 5 Aug 2026
https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands
Slack http://bit
https://arxiv.org/html/2407.04889v1
behavior of other learners
1 Introduction
Setting.
Zero-sum games.
General-sum games.
1.1 Preliminaries
1.2 Algorithms for the learner
1.3 Our results
1.3.1 Zero sum games
Continuous-time games.
Discrete-time games.
1.3.2 A lower bound
https://arxiv.org/html/2407.00419v1
Let ΘΘ\Thetaroman_Θ denote the finite type space, where θ1,θ2∈Θsubscript𝜃1subscript𝜃2Θ\theta_{1},\theta_{2}\in\Thetaitalic_θ start_POSTSUBSCRIPT 1 end_POSTSUBSCRIPT , italic_θ start_POSTSUBSCRIPT 2 end_POSTSUBSCRIPT ∈ roman_Θ denote the private types of the two agents, and 𝜽=(θ1,θ2)
https://arxiv.org/html/2407.20004v1
10 Supplementary Note 10: Exponential Relationship Between ΔDrΔsubscript𝐷𝑟\Delta D_{r}roman_Δ italic_D start_POSTSUBSCRIPT italic_r end_POSTSUBSCRIPT and ΔErΔsubscript𝐸𝑟\Delta E_{r}roman_Δ italic_E start_POSTSUBSCRIPT italic_r end_POSTSUBSCRIPT
Navigation services amplify concentration of
https://arxiv.org/html/2407.14571v1
1.1 Preliminary Work: DataStorm-FE
1.2 Contributions of this Work: DataStorm-EM
2 DataStorm-EM
2.1 Background
2.1.1 DataStorm Workflows, Models, and Streams
2.1.2 DS-Actors and Local Ensembles
2.2 Ensemble Graph, Provenance, and Timelines
https://arxiv.org/html/2407.05763v1
However, centralized observers for plants modeled by nonlinear systems satisfying Ho¨¨o\ddot{\mathrm{o}}over¨ start_ARG roman_o end_ARGlder condition can be found in the recent literature (see, e
https://arxiv.org/html/2407.18010v2
Currently however, the theory of stochastic games in discrete-time does not include a treatment that handles impulse control
https://arxiv.org/html/2407.17766v1
Navigation in Social Mini-Games
I Introduction
II Related Work
II-A Safety Based Methods
II-B Learning Based Methods
II-C Deadlock Resolution Methods
III Preliminaries
III-A Control Barrier Functions
III-B Safety Barrier Certificates
III
https://arxiv.org/html/2407.15077v2
Meanwhile, the sequential updates of HAPPO and A2PO are established upon the assumption that each agent’s update does not depend on and impact the policies of others
https://arxiv.org/html/2506.01844v1
2 Related work
Vision-language models (VLMs).
Vision-language-action models (VLAs).
3 SmolVLA: small, efficient and capable
Overview.
3.1 Model architecture
Vision-language model (VLM).
State, action, and feature projectors.
Visual
https://arxiv.org/html/2407.08254v2
1 Introduction
2 Related Work
3 Problem Formulation
3.1 Multi-agent planning with attrition
4 Attritable MCTS with Regret Minimization
4.1 Overview of the A-MCTS algorithm
4.2 Regret Matching For Cooperative Coordination
4.3 Analysis and
https://arxiv.org/html/2407.06328v2
I Introduction
II Preliminaries and Problem Description
II-A Task Allocation Game Model
II-B Learning Rule, Stochastic Alarm Clock, and Evolutionary Dynamics Model
II-C Payoff Vector Estimation
III Convergence Analysis and Revision Rate
https://arxiv.org/html/2407.20441v1
I Introduction
II System Model and Problem Formulation
III Main result
IV Proof of the main result
V Simulations
VI Conclusion and Future Work
Finite-Time Analysis of Asynchronous Multi-Agent TD Learning
Nicolò Dal Fabbro, Arman Adibi
https://arxiv.org/html/2508.02739v1
2 Preliminary
3 Methodology
K-line Tokenization
Hierarchical Autoregressive Modeling
Model Pre-training
Dataset
Model Training
Inference
4 Experiments
Experimental Setup
Main Results
Prediction Tasks
Generative Tasks
Investment