Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-07-25 · source-backed
BAAI's AREX (24 authors, 124 upvotes on HF Daily Papers) alternates between gathering evidence and drafting provisional answers, then audits those answers constraint-by-constraint. The distinguishing mechanism is a learned autonomous context-update tool that compresses growing interaction history into a compact improvement state with no external critic model. 4B dense and 122B-A10B MoE variants report wins over comparable-scale baselines on BrowseComp, WideSearch, DeepSearchQA and Humanity's Last Exam. Self-improvement inside the context loop rather than via a critic is the architectural idea worth stealing.
Each link below shares sources, entities, or timing with this story.
Deep Research Max on Gemini 3.1 Pro scored 93.3% on DeepSearchQA (up from 66.1% in December) and 54.6% on Humanity's Last Exam. It can combine Google Search, remote MCP servers, URL Context, Code Execution, and File Search in a single API call. Accepts multimodal inputs. Launc...
Farid Zakaria's Self-Executing Linux Format uses binfmt_misc to hand the file to an interpreter that maps rows from a segments table and jumps to the entry point, with the program reading its own file via argv[0]. Symbols, relocations and application data all live in tables in...
He set the 4-byte SQLite application ID at offset 68 to "SELF", decomposed an ELF binary's components into rows across a custom schema, and registered a binfmt_misc handler that hands the file to a self-exec interpreter which queries the tables and runs the program. One file,...
Nearly all cache-compaction research assumes a static context where future queries are known offline, which agents never have. Comparing token eviction against attention matching across proxy-query sources on BrowseComp-Plus and WideSearch, compacting a turn immediately often...
The study names it Solution Hacking: reaching the right answer through numerical search, enumeration, guessing, or answer-first verification rather than a valid derivation. It scales with difficulty, 2.2% on common problems, 28.3% on Olympiad-level, 37.4% on Humanity's Last Ex...
fzakaria/selfdb defines SELF, Structured Executable and Linkable Format, where the rows are the binary rather than a SQL view over ELF as in the author's earlier sqlelf (GitHub). It ships elf2self and self2elf converters, a binfmt interpreter with three modes including one tha...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.