Web This site Trusted
30 result(s) for “okapi bm25 site hotchips pp site github com site via do unit it site answers apache site:arxiv.org” of 37 matched · 883 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: newest result fetched 25 d ago · median age of these results 25 d · 1 of 30 carry a fetch time
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
Instead, it falls on local, personal agents to effectively and safely maintain/utilize such dense person-person (PP) and person-agent (PA) interaction histories
https://arxiv.org/list/cs.AI/new
Extending the pattern-generation paradigm of Neural Cellular Automata (NCA), it navigates the degenerate Boolean search space to satisfy a computational task, rather than regenerating a fixed target state
https://arxiv.org/html/2510.03215v2
Report GitHub Issue
Description:
arXiv is now an independent nonprofit
https://arxiv.org/list/cs.CL/new
With the interaction history, it co-generates ground truth over six recall, reasoning, and trustworthiness evaluation dimensions
https://arxiv.org/html/2607.29281v2
However, it is not obvious how a researcher should direct their efforts to produce evidence toward such objectives
https://arxiv.org/html/2608.03573v1
As shown in Table 2, while SFT improves the target task, it causes substantial degradation in others
https://arxiv.org/html/2608.03703v1
An LETF must trade in the direction of the day’s move at a close that also measures it, so its demand rises in price, and arbitrageurs buying ahead of it enlarge the order by trading at the print, then unload into what they manufactured
https://arxiv.org/list/math/new
It is natural to expect that if many pairs $(x_i,x_j)$ lie at distance close to $1$ from each other, then some clustering phenomenon must occur, implying that a significant number of these pairs are also very close to each other
https://arxiv.org/html/2608.03048v1
6 million tokens and find that it outperforms the recurrent-memory baseline by +6
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/html/2608.03141v1
Transformer architectures represent these inputs as sequences of high-dimensional embedding tokens [14], each corresponding to a modality-specific semantic unit, such as an image patch, a text subword, or an audio segment
https://arxiv.org/html/2608.00458v1
hk; *Corresponding author
Abstract
LLM-based multi-agent systems make decisions based on the aggregated information via exchanging messages across specialized agents
https://arxiv.org/html/2407.16741v3
edu
Abstract
Software is one of the most powerful tools that we humans have at our disposal; it allows a skilled programmer to interact with the world in complex and profound ways
https://arxiv.org/html/2608.02966v1
In conclusion, we show that incorrect answers carry distinct and useful measurement information rather than representing equivalent mistakes
https://arxiv.org/html/2608.03545v1
In TTRL, consensus strength plays a dual role: it reflects both the reliability of the pseudo-label and the distribution of advantages
https://arxiv.org/html/2608.03372v1
Building it answers a practical question: when does a cheap check suffice, and when do you need a model
https://arxiv.org/html/2608.01366v2
1 Better Questions Lead to Better Answers
7
https://arxiv.org/html/2407.03956v3
This system tackles the complex puzzle-solving task by breaking down the problem into smaller, manageable parts, generating SMT (Satisfiability Modulo Theories) code to solve them with a theorem prover, and using feedback between the agents to repeatedly improve their answers
https://arxiv.org/html/2608.01085v1
We introduce a collective evidence-threshold backdoor paradigm for MAS and Boundary-Conditioned Backdoor Injection (BCBI), which constructs counterfactual boundary pairs to separate benign behavior before the threshold from the adversarial objective after it, and learns latent progression aligned with evidence
https://arxiv.org/html/2402.03300v3
com/deepseek-ai/DeepSeek-Math
Abstract
Mathematical reasoning poses a significant challenge for language models due to its complex and structured nature
https://arxiv.org/list/cs.CV/new
40, mean confidence on incorrect answers ranges from 0
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/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/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/html/2608.02665v1
9 pp, with bootstrap 95% CIs excluding zero for all five models, and 5–13% of seeds safe on canonical are unsafe under some reformulation—above a zero stochasticity floor (canonical resampled five times at temperature 0 gives 0/370 new exposures)
https://arxiv.org/html/2608.02617v1
Safe answers therefore require conservative behavior under ambiguity, calibrated uncertainty, and appropriate context-seeking
https://arxiv.org/html/2608.03044v1
Survey opinion data provides a controlled evaluation setting with ground-truth distributions across known demographic subgroups, making it a natural testbed for population simulation capabilities
https://arxiv.org/html/2608.03038v1
First, it demonstrates the value of evaluating statistical reasoning using multiple complementary measures rather than response accuracy alone
https://arxiv.org/html/2608.02621v1
com
Abstract
Legal benchmarks typically score final answers even when models also state legal authority