Research Paper Cockpit

Daily Digest - 2026-10-31

Papers first seen in this daily snapshot.

Daily Archives

Quick jump into generated daily digests.

Research Workflow

Latest digest: 2026-11-17.

Papers

8 visible entries

huggingface Score 13.5

ABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics

2026-10-16 · Xiaohang Yu, Hejia Geng, William Knottenbelt

General AI

Blockchain forensics is adversarial and open-ended: money launderers split, swap, and bridge funds, cut their trail at mixers or custodial services, and change tactics from one incident to the next. Investigators must keep adapting their tracing in response. Yet the immutability of public ledgers preserves every record…

Review
pending
Role
unreviewed
Read
now
huggingface Score 11.5

Scaling Lean Theorem Proving for Real-World Code Verification

2026-10-28 · Debargha Ganguly, Divya Raghunathan, Dejan Jovanović, Vikash Singh, Soonho Kong, Aaron Tomb, Aman Goel, Ferhat Erata, Sam Bayless

General AI

We present EasyProver, a Lean proving system built from recursive agents with isolated contexts, asynchronous search, parallel tactic probing, and an elastic elaboration service. Using an off-the-shelf frontier model with no additional training, it proves 669/672 PutnamBench problems and all six IMO 2026 formalizations…

Review
pending
Role
unreviewed
Read
now
huggingface Score 10.5

Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents

2026-10-25 · Zhenning Shi, Liang Pang, Yongqi Li

General AI

Language agents increasingly act through external tools and interactive environments, making the interface between the model and its executable capabilities part of the decision process. Model Context Protocol (MCP) and command-line interfaces (CLI) can expose the same semantic operations through markedly different mod…

Review
pending
Role
unreviewed
Read
now
huggingface Score 10.5

EPSBench: Benchmarking LLM Agents for Earnings Forecasting

2026-10-28 · Yanbin Yin, Chuyu Xu, Liqin Ye, Jing Peng, Chao Zhang

General AI

Quarterly earnings forecasting requires an agent to connect financial evidence to the income-statement line items that produce a company's reported earnings. We introduce EPSBench, a benchmark for studying this ability across 149 firm-quarters from 86 US companies. Agents read a fixed collection of filings, earnings-ca…

Review
pending
Role
unreviewed
Read
now
huggingface Score 10.5

Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models

2026-10-28 · Yecheng Wu, Song Han, Han Cai

General AI

Self-distillation offers a way to improve reasoning models when a suitable external teacher is unavailable. However, common approaches rely on privileged information to construct a stronger self-teacher, limiting their use when only unlabeled prompts are available. In this paper, we introduce Weakening-Induced On-Polic…

Review
pending
Role
unreviewed
Read
now
huggingface Score 7.5

Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them

2026-10-25 · Aditi Patodiya

General AI

Developers download quantized large language models (LLMs) from public registries to run them locally. None of the registries we examined documented functional testing of their files. We tested all 305 eligible code-capable GGUF tags (the llama.cpp format) across 15 model lines in the official Ollama library, plus 22 p…

Review
pending
Role
unreviewed
Read
soon
huggingface Score 6.5

Proving and Improving the Platonic Representation Hypothesis with JEPAs

2026-10-29 · Randall Balestriero, Yann LeCun

General AI

Whether models trained on different modalities converge to the same representation of the world is central to AI. The Platonic Representation Hypothesis (PRH) conjectures that they do as they scale, but without a proof it offers neither a guarantee nor a recipe. We turn the hypothesis into a theorem. First, we prove a …

Review
pending
Role
unreviewed
Read
soon
huggingface Score 4.5

Unlocking Any-Order Generation in Pretrained Autoregressive Image Models

2026-10-29 · Rishav Pramanik, Marco Pedersoli, Zhaozheng Yin

General AI

Autoregressive (AR) image generators are powerful in principle but inflexible in practice: training with a fixed raster-scan order hardcodes a single factorization of the image distribution into the model, leaving it unable to inpaint, outpaint, or edit at inference time. Existing solutions, including the modern discre…

Review
pending
Role
unreviewed
Read
later